From Ancient to Modern Martech Stack – 10 Immutable Laws

It’s a Data Collector & Cruncher, Insights Producer, Real-Time Processer, and Channel Connector – But wait!  There’s more!

Since the Dawn of Martech Times – The Goals & Principles Remain the Same

For a lifetime (mine anyways) marketers have sought the holy grail of one-to-one customer engagement: Right Customer, Right Time, Right Message/Offer, Right Channel/Place.

In pursuing that goal, those working for enterprises knew to scale beyond mom/pop audience size they needed big tech help –  big data & insights about their customers, at-scale machine learning to calculate what to say and offer, a large & dynamic curated library of messages, as well as direct connections to the ever-growing channels to deliver them – both ones where customers were in channel (inbound) and ones where nudging was required (outbound).

Bringing at-scale tech to this goal started by using big databases.  Those databases held customer account and transaction data and used queries achieving the first step – finding sets of customers with differences in customer behavior.  And those differences proved to be great insights to train models and predict future behavior.  Next, the pioneers matched messages to the predicted behavior segments.  A likely buyer of a certain product just needed an offer for that product.  Then, send that message, get a response, and chalk up higher conversion rates.  

Take, for example, credit card marketers.  They segmented their base into 2 main categories: Transactors and Revolvers.  Transactors paid off their bill.  Revolvers didn’t.   So based on this, they offered transactors incentives to transact more so they would increase revenue (from fees charged to the merchants) and offered revolvers more credit – balance transfers / credit limit increases (where they made fees on the growing balances).  The results:  higher response rates, campaign lift (over controls) and more revenue.

That’s it.  For the next 30 years, businesspeople in a variety of industries – from banking to telco to insurance and others – built out these systems and simply sought more data, improved prediction models, and connected their offers to more channels.  Sounds simple right?  Oh, but it’s not.

Why?  Because big data got bigger, messier, and harder (and more important) to carefully manage.  Getting the right insights from that data was (and still is) tricky.  Establishing data lineage, privacy, and proper governance became crucial.  Algorithms to accurately predict intent, and the right action to take next, evolved – and required controls.  New AI methods sprung up along the way (and continue to do so – with GenAI another example – we’ll get to that later).  And we all know about the proliferation of channels and digital devices.

Martech Stack Ecosystem – Then and Now

Ecosystem wise, not much has changed in the basic framework of a Martech stack since the early 90’s.  Figure 1 shows the main components.  Data is collected from a variety of sources at different velocities.  Some data is distilled before it’s sent, providing insights.   The stack itself produces both data & insights, and those are made available to other systems.  A plan programs the content, data, and strategies employed by the decision system, and gets informed by the results.  AI, both inside and outside the stack, powers predictions.  Finally, ranked recommendations and messages are activated, and married (using metadata) with the appropriate content and delivered to channels.  There, an orchestration layer may dip down to get actual content (e.g., digital images), and then consumers get the output (and hopefully react positively).  Dashboards, reports, and analysis tools help marketers understand the results.

And the goals remain unchanged.  Provide personalized experiences.  Doing so generates lift (higher response and conversion rates) because more relevant offers are presented to customers who are more likely to want them.  It’s not rocket science it’s just marketing science.

modern martech stack

Figure 1: Conceptual Martech Stack and Surrounding Ecosystem

At the high-level, yup that’s pretty much it.  I’ve researched and witnessed this pattern for 30 years.  Attending conferences, following Martech Stackie Awards (2015201620172018201920202021, 2022, 2023.), reading countless analyst blogs, and working with hundreds of enterprise clients across the globe.

The 10 Immutable Laws of Martech Stacks

So, what have we learned?  Since there is an overabundance of data, and technologies of various kinds come & go, lock in on designing the modern Martech stack so that it adheres to principles that have withstood the test of time.

  1. Collect the right data. You don’t need a huge number of customer behavior attributes, but instead the right ones for the business problems being solved (e.g., reduce churn) and so reflect customer intent and cause and effect with likelihood to respond to offers to solve those issues.
  2. Make sure collected data is accurate and, in as much as possible, feed it into your Martech stack in real-time. 
  3. Use segments to study common traits and behaviors.  Assign segment attributes to customers, not the other way around.
  4. Make decisions on individuals, not on segments. 
  5. Use adaptive models to calculate “offer propensity.”  Establish that these models are learning continuously on data you are collecting.
  6. Use one set of engagement strategies and rules for inbound & outbound decisions.  Do not separate this logic and place it into channel systems.
  7. When making inbound decisions, send them immediately. Do not cache decisions into channels waiting for a customer to appear.
  8. With outbound marketing, only send permission-based relevant messages to customers on channels they opt-in and respond to, at times they prefer, and with content that is relevant.  
  9. Use behavior triggers, not pre-set schedules, to determine the right time to send.
  10. Select the latest content just prior to presenting offers (e.g., versions of your offer, that include creative and language variation tests).

And here are a few more pointers: 

You need a few good foundational software platforms (linchpins) that integrate, not 10k technologies (https://chiefmartec.com/2022/10/why-there-are-10000-martech-products-that-kinda-all-do-the-same-thing-but-not-really/). 

Which ones?  Follow this basic advice for the 4 main ones you need, and that must operate well together:

https://customerthink.com/the-final-4-martech-platforms-and-ecosystems/

Compare your design to others that have been successful.  Here is a 2023 stackie winner.  Notice the biggest bubbles:  Content, Execution Platform, Analytics (Insights).

https://chiefmartec.com/wp-content/uploads/2023/04/itau-unibanco-martech-stackie-1456px.jpg

And here is another, centered on using data & AI to power a brain to make decisions during the customer journey cycle (awareness, consideration, decision)

https://chiefmartec.com/wp-content/uploads/2022/05/verizon-martech-stack.png

Don’t drop what you are doing to chase the latest fad.   In other words, don’t fall victim again to the “shiny new object syndrome.[i] ”  Stay the course and be sure to devote some of your tech budget to innovation testing (maybe 10%).   Hopefully, you were already doing that prior to the GenAI hype setting in. 

Speaking of GenAI, test it to see if it helps with Law #5 (finding features for models to learn on) and Law #10 (challenger tests for creative & language variations)

Old saying but it holds true: You can’t manage what you can’t measure.  Measure your program effectiveness by looking at champion creative, promotions, and messaging, and then try new variations, and measure again.

Conclusion

The evolution of the Martech stack over the years has brought about significant advancements in data collection, insights generation, interoperability, and customer engagement. The fundamental goals and principles of delivering personalized experiences to customers remain unchanged. However, as technology and data have become more complex, it is essential to adhere to the 10 immutable laws of Martech to provide the right ingredients for success.

Collecting the right data and ensuring its accuracy in real-time is essential. Segment customers to understand behaviors but make decisions at the individual level in real-time.  Use adaptive models that continuously learn from data and help calculate offer propensity accurately. Inbound and outbound decisions should follow unified strategies and use behavior triggers for timely engagement. Outbound marketing should focus on sending relevant messages on preferred channels.

Build a Martech stack with a few foundational software products that provide insights, content management, and decision management.  The emergence of GenAI offers opportunities to enhance model learning and conduct challenger tests for creative and language variations. However, it is important to test and measure its effectiveness before fully adopting it into the Martech stack.

Finally, measure program effectiveness and iterate with new variations for continuous improvement. By following these principles, businesses can achieve personalized customer engagement and drive higher response and conversion rates.


[i] HBR, https://hbr.org/2021/07/dont-buy-the-wrong-marketing-tech, 2021

Martech Strangelove: How I Learned to Stop Worrying and Love the GPT Bomb

Secrets to Martech Success with GPT

“I can no longer sit back and allow GPT infiltration, GPT indoctrination, GPT subversion, and the international GPT conspiracy to sap and impurify all of our precious human thoughts.”

“Well, boys, I reckon this is it – combat toe-to-toe with the GPT Robots.”

Intro

Some of us are contrarian humans and it’s not in our nature to follow fads.  And so, in November of last year when these pre-trained AI transformers – lurking backstage for years — took the main stage, and then threatened to hack into nuclear codes, those of us so inclined raised our eyebrows and dug in on the side of us carbon-based thinking units.  

I’ve been to two tech conferences in the last month and witnessed firsthand the growing mayhem around this new-age AI.  No doubt one big difference between now and the emergence of the 90’s AI is the speed at which this hype cycle reached a crescendo, and the extent to which GPT is being sold like snake oil to cure all ailments.  And like search in the late 90’s, the speed and ease at which it has entered into the public conscious, and even the accessibility for anyone to use it, has got everyone’s attention.

Accompanied by Langchain, AutoGPT, autonomous agents, prompt engineers, embeddings, and hallucinating large language models – GPT along with a whole new universe of techniques and terms have exploded onto the scene.  Within months all major Martech vendors scrambled fighter jets to launch press releases on yet to be released GPT-infused software.

But then a few days ago, 8 months after G-Day, I popped onto my bank’s website, and the same old UI with the same old poorly personalized experience, sorely lacking self-driving marketing features or an optimized customer experience stared back at me.  Seems maybe deep-learning NLP wasn’t the only thing taking LSD.

The coming out of these inventions is interesting – captivating in fact.  And misunderstand me not, as a big lover of GPT’s rhymes, poems, pictures, and puns, I was very intrigued by its chic performances.  Equally fascinating is that as pack animals, it’s in our human DNA to follow; to want to be part of the latest fashions.   And so GPT gets my alpha dog / tech beauty queen of 2023 vote. 

Still, coming to terms with this latest knighted AI craze — “Sir GPT” — might be prudent.  Without kneeling at its throne, even non-conformists might have to accept it as an eventual buddy, same as happened with smartphones and search a quarter century ago.

So here are 4 tips for Martech leaders on how to approach the GPT mania.  

Tip 1: Do your GPT homework – Separate fact from fiction

With each Martech vendor offering GPT, consider asking these questions:

  1. Show me the GPT features in your software?  When and in which version will this be available?  Can you give me some precise plans around availability?
  2. Can you show me the top features you believe will produce a quantum leap in impact in terms of either lift or productivity (versus features that are simply automating legacy processes)?
  3. What about the value I will get from using these features?  If you can’t show me actual case studies yet, show me projected value, and the math used.
  4. I work in a very large business, so how can I use these features practically and responsibly within an enterprise change management process?
  5. How much will this cost?  Not just the GPT subscription cost, but any other costs that will go into putting this into production.
  6. Can I trial some of these features today?  How much will that cost?
  7. How can I set up a fair test of these features against my baseline?
  8. What are the top 3 features on your roadmap that have nothing to do with GPT?

The answer to that last question will be telling for several reasons.  First, it will give insight into the overall Martech roadmap and strategy, whether balanced — or worse, hastily constructed.  Second, the features mentioned will help with a comparison to your goals and priorities, and how well aligned they are.

As a marketer, consider these as potential use cases:

  • Safely generating alternative subject and body copy for existing promotional offers.  For example, new subject lines for emails, website tile and call to action labels, and offer descriptions.
  • Built-in assistants to automatically configure marketing components that previously required manual set up.  For instance, when creating a campaign in a certain category, and providing basic information, GPT assists in pre-populating fields to minimize manual key entry.
  • For inbound channels, GPT provides more intelligent chat bot assistance.   It does a better job answering basic questions, searching knowledge bases and documentation for answers, and learns from feedback on whether its answers were helpful.

Tip 2: Run some experiments

Consider running a few controlled experiments to gauge GPT’s applied value.  

To ensure the tests are useful, make sure to measure against a known benchmark.   Ask if the experimental design is reproducible, fair, scalable & cost effective.  In other words, will the test be easy to set up?  Can it be run repeatedly in a short period of time (producing adequate experimental results to measure against the benchmark)?

  • To test new copy, pit GPT’s proposed writing against the champion.   Randomly assign GPT’s offer to a 2% sample of customers.  Does it outperform the champion over time?
  • Do the built-in assistants really save time in configuration?  Or is it a bell/whistle that looks good in a demo, but that real-life users won’t use?  Do usability testing with the real users to find out.
  • Do the chat bot interactions result in higher NPS scores?   After each chat bot session, ask for an NPS score for the session, and compare that with current scores.

Tip 3: Study the results and invest accordingly

This tip may seem obvious.  However, the knee-jerk reaction might be to adopt the new feature(s) if the test results show any improvement over the baseline.   But make sure to weigh the total costs versus the actual benefits.  If the lift is meager, but the costs high, the ROI might not be there.

In addition, network and study your peer’s experiences as the Guinee pigs.   Are the projects going well?   Are they producing the expected results?   Is there a stark difference between what was on the glossy brochure versus how the real-life experience turned out?  In other words, learn from the mistakes of others.

Tip 4: Stay the course – with a solid overall DNA – Data aNd Analytics – Modernization Strategy

Massive data and fine-tuned analytics are the core materials of GPT (or any successful application of AI), and both must be the genome that fuels every company.  Firms must weave data & analytics into their organizational fabric to fundamentally transform two aspects of their business in careful balance: a hyperfocus on personalized customer experience while becoming operationally efficient.

But where to start?   Here are three things to concentrate efforts on:

  1. Implement advanced analytics to improve customer experience: By compiling and analyzing customer data across a variety of channels, you’ll gain insights into their preferences and behavior. This will support personalized services, development of appropriate products and services, and improved customer engagement.  In addition, use predictive analytics to identify the best channels to reach your customers.
  2. Optimize operations and reduce costs through data-driven decision-making: By analyzing operational data, you can identify inefficiencies and bottlenecks in your processes. This can help streamline operations and reduce costs. For example, banks can use data analytics to optimize loan approval processes, improve credit risk management, or reduce fraud.  Telcos can analyze real-time network performance data and even identify potential issues before they occur and take proactive measures to prevent them.
  3. Build a data-driven culture and foster data literacy among employees: To fully leverage the power of data and analytics, you need a culture that values data and encourages data-driven decision-making. This requires not only the right technology and infrastructure but also a workforce that is knowledgeable about data and analytics. Winner brands will provide training and resources to help employees develop data literacy skills and create a culture that encourages experimentation and innovation.

Conclusion:

In the end, though there will be a few lucky hares, for the majority the tortoise-like approach is the winning strategy.

Oh, by the way, I took my intro words, plugged them into GPT, and gave it the following prompt. 

————————-

GPT prompt: Write me a pun based on the fable of the tortoise and the hare using this prose <inserted above intro words>

————————-

GPT response:

In the world of AI, a contrarian thought I bore,

As GPT took the stage, its hype soared and more.

But now I’ve come to terms with this AI craze,

Sir GPT, they call it, deserving some praise.

I won’t kneel at its altar or its throne,

But I’ll let it into my life, like Google once known.

Tech conferences showcased mayhem and noise,

With Langchain, AutoGPT, and AI toys.

Martech vendors scrambled, their releases to boast,

Yet my bank’s website remained a poor host.

No self-driving marketing, no personalized flair,

Perhaps deep-learning NLP was also on a wild tear.

These recent inventions captivate, it’s true,

And I love a good pun, rhyme, or verse that’s new.

But as pack animals, we follow the alpha’s lead,

And GPT claims my alpha dog award, indeed.

So here are four tips for Martech leaders to heed,

Do your GPT homework, experiment and succeed.

Study the results, invest wisely in this race,

But remember, the tortoise’s approach sets the winning pace.

————————-

This robot is kind of a cute poet.  But Sr GPT, you didn’t exactly write a pun, so allow me to assist you:

If one takes the hare’s approach you may be “hare today but goon tomorrow.”

CDPs Then & Now – The Customer ID (Identification & Data) Problem

In November 2019 perhaps you caught this article: “To CDP or NOT – 3 tips – then you decide.”  The main takeaway – the CDP space is a quasi-market with a mixed bag of firms coming from different lineages and different levels of capability, maturity, and focus.  The conclusion: buyer beware and standby.

That was BC – Before COVID-19.  Since then, what hasn’t changed about the world?  And like everything in 2020, the CDP market was not immune to upheaval.  And although the basic premise for adding a CDP into the Martech stack is still the same:

  1. Help resolve customer identity
  2. Rationalize and manage customer data
  3. Make that data accessible to other systems

…what’s changed are the vendors involved, and their core and extended capabilities, which are substantially different nearly three years later.

Most markets appear as nebulous categories, and the CDP market was no exception.  But as buyers and vendors evolve, dust settles, and the picture becomes clearer.  Still, two important aspects of what a CDP should supply loom large and are worthy of close inspection.  Namely, providing customer recognition/identity management and distilling the right (and righteous) customer data into meaningful insights.

Considering those key features, let’s explore a few of the big changes since November 2019:

  • The huge marketing cloud players entered the market:  Adobe, Oracle, and Salesforce
  • More consolidation took place, with small CDPs swallowed up by an interesting mix of companies
  • Perilous new milestones reached for third-party cookies and stealth consumer tracking

Stick with me.   You’ll get insight into these three changes, three tips, and some final thoughts.

Marketing Cloud Titans Enter CDP Fray

Adobe Real-Time CDP

In early 2020, Adobe entered the CDP ring with Adobe Experience Platform’s Real-Time CDP, promising to “Combine all individual and company data — internal and external, known and unknown — into a standard taxonomy that can be activated in real-time.”[i]  A tall order indeed.

Although certainly set up to collect digital data by way of Adobe Launch & Analytics, Adobe’s aggressive mission to combine “all data” for B2C and B2B across known and unknown, lacks focus and gives reason for pause.

Adobe has fared well in providing digital marketing data & support for early-stage customer journey activity, with its first-generation web analytics and tag management (by way of its Omniture acquisition over 10 years ago), followed by its subsequent purchases of Demdex (third-party cookie data-management platform), and marketing automation firms like Neolane (B2C) and Marketo (B2B).  Yet with the third-party cookie tracking foundation crumbling as the final browsers outlaw it, they’ve had to look for another way.  So far, that appears to be using CNAME record cloaking, which in effect is just a clever DNS hack to circumvent gaining explicit permission to track. 

The ultimate jury and judge (the consumer) may not approve of this tactic (once they discover it).  Further, with a shortage of direct access to first-party behavior data, customer analytics depth, and channel breadth, Adobe still struggles to develop deep customer understanding and natively/performantly enrich its customer profile.  And other than collecting raw digital data in real-time, not much else about Adobe’s CDP is real-time and insightful.  Adobe nonetheless plows forward with bold statements of real-time and unity that potential CDP buyers should take with a grain of salt.

As a major marketing cloud player, Adobe will eventually amass more digital data, improve its signal detection, and get more apt at activating those signals and audiences in acceptable ways.   But for now, buyers should beware of completeness claims, tracking practices, data feeds and speeds, and external integration features.

Oracle’s CDP

Interestingly, googling with the term “Oracle CDP” yields a top result pointing to an Oracle whitepaper-like webpage espousing that a “customer data platform (CDP) is software that collects and unifies first-party customer data.” [ii]  So far so good.  

Reading on, the article mentions “first-party data” 11 times, never mentioning third-party data until the final punchline at the end, where the author claims that a Customer Intelligence Platform (CIP) is different from a CDP because it “incorporates anonymous, third-party data as well as first-party data.”    It’s here that Oracle tries to differentiate its CDP, Oracle Unity, from all others.  That differentiation attempt falls flat, and is oddly fascinating on three fronts:

  • Oracle has almost no choice but to take this approach, since it spent $400m on BlueKai in 2014, one of the world’s leading third-party data trackers.  As such, Oracle wants the buyer to believe they get a premium from contracting with a CDP that can merge third-party data.
  • Oracle claims it’s not really a CDP, but instead differentiates as a Customer Intelligence Platform (CIP), and not just for marketing.   Amusingly, in my June 2019 article I advocate for a CIP – The Final 4: MarTech Platforms and Ecosystems –  yet with the middle letter short for insights about individuals attainted from first-party data, not general intelligence.  Very different CIPs indeed.
  • The reason for the demise of the cookie-based cottage industry and third-party data is that it was built on a house of cookie cards, gathering and brokering consumers’ data without explicit permission, and inherently unreliable as a good proxy for consumer intent & behavior – one of the major tenants for a CDP.

Given this, be careful with Oracle’s CDP (or CIP) solution, with its bias toward third-party data, paid media channels, and early-stage acquisition use cases.  Purchasing one means buying into the value of third-party data and acquisition use cases, while not solving for data-driven, real-time 1-1 customer engagement use cases, deeper into the relationship, on owned channels.

Salesforce’s CDP

Late in 2019, as the virus was unknowingly spreading, Salesforce began spreading the news about its new Customer 360 Truth, claiming it had a product with “a new set of data and identity services that enable companies to build a single source of truth across all of their customer relationships.“ [iii]  And although at the time they didn’t call it a CDP, they were quacking as if it were one, and funny enough in April 2021 relaunched it as a CDP. [iv]

In 2019, in classic Salesforce fashion, they announced a not-ready-for-prime-time CDP-like product, C360, with pages of fine print.  Like a theater stage with a kitchen viewed from afar, it might have appeared fully equipped.  However, on closer inspection, some of the supposed appliances were but props with no cords to plug in, no motor to run them.

And even on re-launch in May 2021, they simply slapped existing separate products such as Tableau and Mulesoft onto the wrapping paper of the Salesforce CDP.  Further, like most CDPs (except ones that come from the web analytics space, such as Tealium and Celebrus) everything is based on creating customer segments and sharing those in less than real-time for activation instead of taking an individual personalization approach and sharing in real-time.

Thus, rip off the cartoon marketing wrappers, and look inside the box and inspect all the parts for function and fit before buying.

CDP Market Consolidation

In addition to the entrance of the above big three, Microsoft and SAP also announced CDP solutions.  Before November 2019, 18 acquisitions took place. Since November 2019, 8 more further transformed the CDP landscape:

  • IgnitionOne bought by Zeta Global – December 2019
  • AgilOne bought by Acquia – December 2019
  • Evergage bought by Salesforce – February 2020
  • Segment bought by Twilio – October 2020
  • Exponea bought by Bloomreach – January 2021
  • BlueVenn bought by Upland Software – March 2021
  • Boxever bought by Sitecore – March 2021
  • Zaius bought by Optimizely/Episerver – March 2021

What’s the takeaway?  Dust is still flying in this market.  And if you are betting on one of the 100+ vendors calling themselves a CDP to plug key gaps, especially in foundational areas such as identity & data management, consider whether their future is secure, and they’ll continue to go in the same direction, as it could impact yours.

The Calamitous Cookie Crisis – Customer Identification and Tracking

In January 2020, Google announced plans to end support for third-party cookies in Chrome in two years.  Late-breaking news is that in June 2021, Google said they will delay until the middle of 2023.  But cookiepocalypse is still coming.  With less than two years until that deadline, ad-tech companies, and ad agencies alike are scrambling to find workarounds for web behavior identification and tracking. 

Case in point – The Trade Desk and ad agency Publicis (who bought the database marketing firm Epsilon in 2019) are teaming on a digital advertising solution built around the new open-source identification scheme called Unified ID 2.0.  Initially developed by The Trade Desk, Unified ID 2.0 obfuscates a consumer’s email address, using a technical hashing technique to protect consumer privacy.[v]  

As of May 2021, The Trade Desk says it already has over 170 million profiles obtained with consent.  But long-term success depends on an even bigger pool of email addresses (e.g., more consumers opting in than opting out), and that means enough publishers adopting the standard, and obtaining consumer consent.  Since history has shown consumers will opt-in without reading terms and conditions, it may have hope, especially in places like the US and Asia, so stay tuned.  My advice – read before you click, as it’s essentially agreeing to be a target of every participating company. 

In addition, SAP and Akamai bought traditional sign-on companies Gigya and Janrain respectively, going the route of obtaining social sign-on solutions to gain access to customer identification and tracking capabilities.  And although Okta, who acquired rival Auth0 in May 2021, hasn’t called itself a CDP (yet), they are a force in the customer authentication and identity space.  

What does this have to do with CDPs?   Well many ad-tech companies, formerly calling themselves data-management platforms (DMPs) during the third-party cookie era, now claim to be CDPs.  Keep in mind, however, they built their solutions to manage third-party data and cookies and to target based on these spurious methods, and not on first-party data and known identities.  Ultimately, without a strong first-party data foundation, those DMP CDPs have a limited shelf-life and are poor investments.

CDP Selection Tips

Tip #1 – Study their specialty

Keep in mind that all vendors started with a core offering.  That tells a lot about what they’re probably good at.  When interviewing a job applicant, there’s a reason why we inspect someone’s background (work history, school they attended), as it gives insight into how they’ve honed their craft. 

No vendor (not even the big ones) will be able to supply best-of-breed capabilities to handle all stages of a journey, from the anonymous browsing steps to phases deeper in an authenticated relationship.  Nor will they be able to major in more than a handful of the dozen or so capabilities the collective CDP market covers:

  1. Data collection
  2. ETL – Extract, transform, load (including cleansing and householding)
  3. Identity stitching and management
  4. Real-time data insights
  5. Predictive analytics
  6. Recommendations and decisioning engines
  7. Journey (cross-channel) orchestration
  8. Owned channel marketing automation and e-message services
  9. Digital advertising
  10. General (business intelligence) customer data activation
  11. Internal query, reporting, dashboards, and attribution analysis

Most native CDPs came up focusing on one or more of the first 3.  And with no official CDP magic quadrants or waves by major analyst firms, many others have conveniently slapped the CDP label on themselves. So, decide where you have the biggest capability gaps and needs along the customer journey, where a data-driven solution will drive better outcomes and more value, find matches, and select accordingly.  Also, if gaps exist mainly in areas 4 – 10, look beyond the CDP market, as there are a multitude of vendors not calling themselves CDPs that major in these areas.

Tip #2 – Demand real-time response times

When considering the claim of “real-time,” (which is a critical capability to take CX to another level) look beyond single components, such as the speed of data collection, or placing data onto a customer profile record.  Instead, inspect the entire data/event -> insights -> decision journey and ask:

  • “Can that entire trip be accomplished in an SLA (Service Level Agreement) under 200 milliseconds?”
  • “Can the vendor do that at scale, for millions of customers and 1000’s of interactions per second?”

Why 200 milliseconds you ask?  Because as a consumer, do you want websites you use to be slower?   As a person responsible for the website, will you allow anything new to slow down page loads?   I bet the answer to both is no.   So if your new CDP is going to play a role in providing better real-time digital experiences, it better not take up much of the two-tenths of a second response time budget.

Tip #3 – Demand real-time insights

Look for a CDP that can supply real-time data insights, with a library of these for your industry.  This looms so largely in reaping unfair benefits from a CDP investment because not many CDPs do this, and it’s how you’ll move the needle on customer experience.  Can you do this today?  Can you find customer behavior diamonds in the deep mines of digital data, surface it, polish it, and immediately pass it to a customer decision hub?  Not many can.

For instance, detecting consumers’ heightened but fleeting interest in specific products, refining that raw data into curated signals, passing them to a decision engine in real-time, so it can trigger special and immediate actions.  Very few CDPs can do these things – in that order – fast enough.  An example: a consumer on a banking website, researching mortgages [again] in the final stage of selecting a mortgage provider. 

So, look for a CDP that can solve this problem. There aren’t many.  You’ll add something special and unique that few can do.  Celebrus is one solving this exact problem:  collecting the right behavior data, making sense of it in the form of a signal library, passing those signals to a decision authority in real-time, so it can act in the moment.

Conclusion

Big is not always better, but it’s always bigger.  And although selecting a large outfit as a CDP provider gives some assurance that the solution will be around in a few years, that doesn’t necessarily equate to the best CDP solution.  Doing business with a mega-CDP vendor rarely means faster, more seamless interfaces and deep expertise.  On the contrary, expect bigger integration costs, longer wait times, custom work, and more patience required.  And if selecting a big CDP is for “one throat to choke,” try finding that elusive throat inside a tech behemoth with 50,000 employees who have swallowed up 20 companies on the way to building their marketing stack and CDP.

Conversely, using a smaller player has its tradeoffs.  Besides the risk of being bought, or folding up, inevitably their capability focus will be esoteric.  So, carefully inspect core competencies. Look for a CDP that compliantly tracks customers, collects data in real-time, has a signal library fit for purpose, and can interoperate with a decision hub. That way, you’ll get differentiation leading to better customer experiences from your CDP investment.


[i] Adobe.com, https://business.adobe.com/products/real-time-customer-data-platform/RTCDP.html, June 2021

[ii] Oracle.com, https://www.oracle.com/cx/customer-data-platform/what-is-cdp/, June 2021

[iii] Salesforce.com, https://www.salesforce.com/news/press-releases/2019/11/19/salesforce-announces-customer-360-truth-a-single-source-of-truth-for-every-customer-across-the-worlds-1-crm-2/, November 2019

[iv] Salesforce.com, https://www.salesforce.com/news/stories/salesforce-cdp-innovations-make-customer-interactions-smarter*/, May 2021

[v] The Wall Street Journal, https://www.wsj.com/articles/publicis-groupe-signs-on-to-use-trade-desks-alternative-to-cookies-11617883217, April 2021

The Hyper-Personalization Paradox: being relevant without crossing the CREEPY LINE

Brands are using AI to drive hyper-personalization, but can it also help them avoid being hyper creepy?

hyper-personalization

Source: https://www.adclarity.com/2015/04/digital-marketing-2015-hyper-personalization-display-ads/

Apparently, I have 8 seconds to grab your attention, so here goes.  What if I personalized every aspect of this blog for you?  That is, I knew so much about you – your reading behavior, the writing style you prefer, subjects you love – took all of it into account, and assembled these words and pictures just for you?  Would you find that creepy or cool?

At our conference in Las Vegas recently, I was a guest on Sam Charrington’s, podcast series “This Week In Machine Learning and AI.”  In that episode, we discussed a similar hyper-personalization scenario, where an automotive company used intimate knowledge about a consumer and her connected car to custom-tailor each marketing and service treatment[i].  And half-way through (at 23:07), Sam observed that although “consumers appreciate personalized experiences,” it can go too far and “sometimes come across as creepy.”

And suddenly, we both realized something.  Customer experience experts haven’t used AI to govern this.  In other words, CX pros personalize without recognizing if their personalization levels are approaching creepiness.

Which led to this question: can creepiness be quantified?  And if so, with that knowledge, could a company effectively use it?  With the right tooling, could they safely test and simulate how far personalization should go, carefully delivering each customer a tailored experience with the right level of relevance and value, without crossing into their creepy space?  Simply put, hyper-personalizing without being hyper-personal — the personalization paradox.

You’re marketing is creeping me out

Creepy land is that forbidden zone where consumers call out businesses for using personal data and revealing insights that are a bit too private.  And though consumers increasingly want personalized experiences (according to a recent Epsilon study[ii], 90 percent of consumers find it appealing), ironically, they will happily make examples of brands that invade their personal space.

No brand wants a creepy reputation as it implies:

  1. Stalking, snooping, or spying; collecting personal data and invading privacy
  2. Revealing something private, no matter how valuable the insight
  3. Not having customers’ best interests in mind
  4. Ill-intent, even when there isn’t intention to do harm

With big data galore, a culture of a data sharing, and pressure to mass personalize to remain competitive, you need ways to safely and systematically explore the creepy line’s location without ever crossing it.  Understanding what customers expect and why they love a product (or don’t) is crucial to great personalization.  Avoiding a creepy moniker means effectively steering clear of areas that are, frankly, none of your business.  And if the customer says it’s none of your business, it’s none of your business.

Today, the digital world abounds with copious quantities of demographic, psychographic, and behavioral data.  There’s a sea of it, because for decades companies have wired up clients and monitored them like lab rats.  And with more IoT tech and data coming every day, firms increasingly misuse it, giving customers more reasons to demand privacy.  The problem is the definition of what’s private and sensitive can be different for each person.  Hence the dilemma: under personalize and risk being labeled clueless, not cool, and worse miss out on revenue; over personalize and risk breaking trust and doing irreparable damage to your reputation.

Sorry we’re creepy. We apologize for any inconvenience 

Customer engagement professionals need new and scalable ways to survey buyers, collect preferences and permissions, sense their intent and moments of need, and personalize appropriately.  So, they need ways to test where that creepy boundary is.  That line is fluid and ever shifting and finding the right level of personalized insights and recommendations without crossing into risky territory is never without some uncertainty.

Where that line lurks changes with time because initially customers may be leery of something, then later adapt to it.  It also changes because privacy legislation changes, individual consumers have distinct levels of sensitivity, and varying levels of awareness. It can even differ by geography.  For instance, a 2016 study of 2000 consumers in Europe found that 75 percent were uncomfortable with facial recognition software used to target them with personalized offers (consumers in the US were much less sensitive)[iii]

Data-driven marketers have evolved their practices (Figure 1) using data to acquire more customer knowledge which in turn powers more personalization.  Over time, more marketers have evolved their practices, from the general advertising Mad Men approaches of the 1960’s to the super-personalized, AI-Powered approaches possible today.  It also highlights how that pushes them closer to the creepy space.

hyper-personalization evolution

Figure 1: Evolution of Data-Driven Marketing

Here’s the bottom line: if a given customers perception is it’s creepy, it’s creepy.  And depending on who slaps that label on, and whether their rights that have been violated, firms may face legal battles, fines, and reputation damage leading to significant commercial impact.  For instance, potential fines for GDPR privacy law violators can reach 4 percent of a firm’s revenue (up to a maximum of €20 million).

And none of that is music to a businessperson’s ear.

Creeping toward creepy

In 2014, Pinterest managed to spam a major segment of customers when they sent emails to unengaged women congratulating them on their upcoming weddings.  And Shutterfly made an even bigger spam faux pas that same year, congratulating women on the birth of babies they didn’t have.

In Figure 1, these events fall into the SPAM circle because marketers placed people into the wrong macro segments, and the resulting emails were both irrelevant and hilariously erroneous.   Clumsy customer experiences indeed, but not creepy-smart marketing.

Here are some other examples of Mad Men SPAM marketing:

  • You market wedding offers after a wedding – low sensitivity
  • You market wedding offers after a cancelled wedding – high sensitivity

On the other hand, the risk of being labeled a creepy marketer increases when knowledge of customers goes up, insights increase, yet marketers fail to understand an individual’s sensitivity to certain marketing actions.

For each marketing treatment, you need to determine if it will be creepy to everyone or only some:

creepy meter

Figure 2a:  Creepy Meter detecting creepy treatments

If it’s clearly creepy to everyone, during the pre-market approval process you should reject it.  But, if its potentially cool to some, and creepy to others, then provided you can discriminate at runtime using eligibility rules, you can approve its use for those who will find it cool.

To do this, get a readout on consumers’ sensitivity to hyper-personalization.  Build a model that learns this, and use this score to select, by individual, the levels of personalization they’re eligible to receive.

creepy index

Figure 2b:  The Creepy Sensitivity Index readout on each consumer

Here are a few examples of events, corresponding covert marketing approaches, and creepy readings:

 Event Covert Marketing (but not illegal) Creepy Meter Approve?
Hospital admittance / serious health issues detected Mortuary makes discount offers Extremely creepy Reject
Conversation recorded (without clear permission to use for marketing) Ads for products related to keywords in the conversation (e.g., pet toy video recently, which illustrates the point yet is likely a hoax) Very creepy Reject
Facial recognition or location detection Upon a patron entering a branch or store, their profile & preferences are relayed to a salesperson Borderline creepy Conditional
Consumer traveling; recent activity and calendar scanned Push notifications offering travel recommendations based on triangulating travel intent and destination Borderline creepy Conditional
Consumer browsing a web page with product offers Website background, images, language, offers, and other page fragments hyper-personalized Borderline creepy Conditional

Table 1: Examples of potentially creepy marketing

Leading-edge 1:1 marketers are constantly listening for keywords, tracking interaction device, time & location, codifying behavior, sensing mood, recording preferences, and using that knowledge to hyper-personalize with content variations in the millions.  The risk, however, is meandering into that forbidden creepy zone (even if it’s legal), so discerning this by customer by treatment is vital.

Suggestions

As you move into deeper levels of hyper-personalization, do so deliberately and methodically, fully grasping the implications before rolling out.  Consider taking this approach:

  • Collect only data that matters to your ability to personalize specific experiences – that your customer will value. For example, if you sell insurance, you don’t need to understand pet preferences unless you’re selling pet insurance.
  • Start with simple / minimal risk personalization strategies. These should easily pass the creepy test.  For instance, if you can tune you web experience to shopper color preferences, do it.  No one will find that creepy.
  • Gradually apply regional and demographic personalization strategies.
  • Use AI to crawl your products and content to extract taxonomies, attributes, cross-classifications, and descriptions. This will help better match customer intent and preferences to products that will match needs.
  • Use AI to match the right products to clients (making relevant recommendations) and doing so in a personalized way that enhances their experience
  • Use sampling to test hyper-personalization treatments, selecting a wide variety of customers.  Essentially, you get a stratified sample of creepiness raters.
  • In general, avoid even borderline covert marketing unless you have a firm handle on any backlash that might result if customers discover it. In a recent survey, most consumers (81%) think firms are obligated to disclose they’re using AI – and how they’re using it.[iv]
  • Be sensitive to consumers’ preferences for public recognition.  Some might love it if you great them by first name and show appreciation for their loyalty in public.  A few, however, may be mortified.

Hyper-personalization requires great data, great technology, and great sensitivity.  With GDPR now in effect, most businesses are proactively disclosing their data collection practices and privacy policies.  As consumers, we’re consenting to and accepting new privacy policies more than ever before, and in some cases, we’re even reading and understanding them.  Less clear, however, is exactly how that data is used, combined with other data, and when it might show up as an insight, recommendation, or hyper-personalization – and again, which of us might be freaked out by this personalization.

AI is driving personalization to new levels.  There’s no stopping that.  It automatically figures out what works and what doesn’t.  Techniques, such as Bayesian algorithms, quickly learn which offers work, when, and in which channels.  Others, like collaborative filtering, find which products pair best, that in turn drives cross-sell and bundling strategies.  Design of experiments and monitoring devices measure the impact and enable fine tuning.

What’s missing, however, are tools to sense consumers’ sensitivity to personalization, so overt practices are optimized with the right people, and so covert methods are prevented from ever reaching production, or if they are approved for use, are carefully applied.

The study shown in Figure 3 provided some proof that overt personalization pays off.   Yet the very definition of overt blurs as AI improves, content becomes hyper-conditional, and levels of personalization get more complex.  Thus, you’ll need more sophisticated ways to gauge levels of personalization relative to creepiness, and the sensitivity levels of different people.

personalization

Figure 3: Overt vs covert personalization performance[v]

Conclusion

Great marketers push beyond perceived barriers by understanding customers, knowing products, and then elegantly combining creativity and technology to provide valuable recommendations and experiences to customers.  Ironically, when done right in the eyes of the receiving consumer, they don’t appear to be selling anything; instead simply providing a service.

With website personalization, one-to-one content, natural language generation, image recognition, and countless other AI tools, businesses inexorably march toward hyper-personalization.  Make sure you manage it, so you’re always cool and never creepy.


Endnotes:

[i] https://www1.pega.com/insights/resources/pegaworld-2018-pegas-ai-innovation-lab-sneak-peek-and-your-vote-counts-video, June 2018

[ii] http://pressroom.epsilon.com/new-epsilon-research-indicates-80-of-consumers-are-more-likely-to-make-a-purchase-when-brands-offer-personalized-experiences/, January 2018

[iii] https://www.forbes.com/sites/fionabriggs/2016/07/04/fingerprint-scanning-is-cool-but-facial-recognition-creepy-new-richrelevance-survey-shows/2/#493b953f3d68, July 2016

[iv] https://www.richrelevance.com/blog/2018/06/20/creepy-cool-2018-richrelevance-study-finds-80-consumers-demand-artificial-intelligence-ai-transparency/, June 2018

[v] https://www.sciencedirect.com/science/article/pii/S0022435914000669#abs0005, March 2015

 

4 well-intended Marketing Automation BAD HABITS to break

Let’s face it.  No one sets out to botch something up or fall short of reaching a goal.  When marketing automation was in its infancy, and pioneers like Don Peppers, Martha Rogers, Tom Siebel, and Paul Greenberg envisioned marketing and CRM systems in the mid 1990’s, they set the right vision, believing great customer relationships could be initiated, fostered, and brought to scale with the right data and technology.  Essentially, their collective creed was:

  • Focus on the individual customer (e.g., be one-to-one and customer centric).
  • Manage the relationship by understanding customers’ buying cycles, needs, and behaviors across the marketing, sales, and service functions.
  • Use that knowledge to custom-tailor and personalize the experience.
  • Use technology to deal with the scale required by larger businesses.

Thirty years later, sadly, this vision still seems out of reach, or at best, only partially realized.  So why is that?  What’s held back the realization of the vision?  What are we still doing wrong?

Here are four unhealthy habits of nearly every marketer (so the good news is you’re not alone).  Fix these, and you’ll get a distinct advantage, and get closer to marketing optimization and CRM nirvana.

 

Bad habit #1 – Focusing on customer segments and not individuals

Customers are individuals.  Each has unique characteristics, nuances, and contextual needs that define who they really are.  And though we’re awash in a wealth of unique behavior data, it’s a common mistake to continue trekking on the beaten path, making decisions based on segment characteristics rather than individual ones.  For years, we’ve slotted customers into segments because we had no other choice, oversimplifying who they really are.

1 to 1 marketing automation

It’s understandable in the initial stages of relationship management that businesses make broad customer classifications such as:

  • Returning visitors
  • Mobile visitors by geography and device type
  • Registered users by gender and age (leading to segments like Millennials, Gen Zs, and Gen Alphas)
  • Non-responders to an email campaign

Yet after these customers repeatedly interact and transact, clearly stating their implicit and explicit preferences, continually handing over lifestyle and contextual data, there’s no excuse for still making generalized, segment-based decisions.  We’re spending millions collecting, storing, and refreshing specific behaviors and preferences, so we should use this data to drive individualized decisions and to customize treatments.

In a recent paper titled “Crossing the chasm: From campaigns to always-on marketing,” [i] Rob Walker and Matt Nolan contend that “building audiences using segmentation is a process that introduces severe challenges such as compromised relevance, unscaled labor, and collisions and conflicts.”  They go on to suggest using a next-best-action approach, describing it as one that “targets individual customers, rather than segments – leveraging their unique needs, preferences, and context.”

 

Bad habit #2 – Focusing on selling products instead of customers’ needs

Sounds crazy, right?   How else will we make money if we don’t sell products?

Still one of the cardinal sins holding back modern marketers is focusing strategy and tactics solely on selling products.  By doing this, we’re exasperating two problems:

  1. Product owners, incented to relentlessly push their products, bombard consumers with ill-conceived campaigns containing messages and offers that conflict, overlap, or worse, aren’t even applicable. When viewed through a customer’s lens, these promotions have little to do with their actual needs.  As such, marketers often completely miss the relevance mark.
  2. Even when a product fits, companies fail to provide well-timed promotions, convenient services, and a context-sensitive experience. Oblivious to the individual’s situation, they make company-focused timing and interaction decisions, such as blindly promoting a product simply because ad budget might otherwise expire, or failing to promote crucial services in conjunction with the product..  Consequently, tactics are entirely out-of-synch with the customer’s buying cycle and experience expectations.

Together, these problems compound customers’ negative brand perceptions.  Rather than providing a stellar buying service, well-intentioned marketers inadvertently (and increasingly) overwhelm, turn off, and tune out consumers.  Essentially blind to journey requirements, marketers miscalculate customers’ value calculus, timing preferences, and the overall interaction experience they need and expect.

In study after study (year after year), consumers and brands acknowledge these issues, both resoundingly stating their desire for solutions.  For example, in 2012 the Corporate Executive Board (now part of Gartner) surveyed more than 7000 consumers and 200 CMOs, finding that what consumers want from marketers is relevance and “simply, simplicity.”[ii]  That was 2012.  It’s 2018, and not much has changed.

If corporations keep strategy oriented on selling products, customer relationships will remain transactional and experiences sub-optimal for many more years.  Maybe we’ve forgotten what the R in CRM stands for.  It was put there to remind us that what matters most is long-term relationship building.  Our quest should be to unravel the mystery of a customer’s ever-changing needs, their journeys, and what drives their loyalty.  Our job is to use that knowledge to create custom-tailored experiences.

 

Bad habit #3 – Building channel-based versus coordinated intelligence

Shortly after September 11, 2001, the US government came to a stark realization that its various intelligence agencies were massively disjointed and compartmentalized.  This hadn’t happened overnight.  It was years in the making, and although for decades ample resources were poured into each agency, no one agency was responsible for coordination.  Attempting to solve this problem, the government established the Department of Homeland Security.

channel intelligenceIn a similar vein, some firms have built up marketing automation and CRM intelligence in silos for over 30 years.  In each channel (e.g., email, contact centers, web), they’ve poured substantial resources into projects aimed at beefing up customer intelligence.  Each channel amassing data, rules, and intelligence, but no one designated as the coordinator, and information rarely shared.  Subsequently, as more channels emerged, the problem grew larger. Today, many companies have 15 or more channels to manage, and no coordinating function.

To provide wonderful experience, brands need a function responsible for coordinated customer analytics, intelligence, and decision making, such as depicted in Figure 1.  Its role is straightforward:

  1. Collect interaction intelligence and contextual data from each touchpoint, and connect it directly to a system that can leverage that information immediately.
  2. Be brain-like, tracking behavior patterns in real-time, sensing needs, and using analytics to dynamically calculate value, comprehend preferences, and predict intent.
  3. Play the arbitrator, weighing an individual’s needs against corporate initiatives, policy, risk tolerance, budgets, and economic goals. Make instant and well-balanced decisions, track the results, and learn from each decision.

 

engagement hub

Figure 1: Engagement hub provides coordinated omnichannel intelligence

Think of this, not as another physical department, but instead as a virtual customer-centric hub. Designed from the ground up to be connected to all customer touchpoints, it’s journey oriented versus channel centric.  Cognizant of what transpired, why, and what’s best to do next, its embedded strategies and rules act as a real-time arbitration committee – making data-driven decisions in milliseconds versus months.

This hub is also more than a customer data platform.  It’s an end-to-end engagement hub responsible for not only gathering and coordinating intelligence, but also gleaning real-time insights and taking action.  To deliver on that, it manages key data, customer analytics, corporate rules and processes, and channel interfaces.  In a calculated and auditable fashion, it makes recommendations, delivers them to touchpoints (the channel apps fine tune the experience), and it learns from a systemic set of impressions and responses.

 

Bad habit #4 – Worrying primarily about marketing automation and technology, instead of experience

Automation, and the technology that enables it, efficiently repeats tasks.  That’s great, if you computerize the right tasks that deliver the right experience.  Look at it this way:  spammers are very effective at marketing automation.

Above all, to achieve lasting loyalty and build value, avoid the temptation to recklessly make existing marketing processes more efficient.  Granted, some existing tactics may work, yet chances are many need to be revamped (or ditched entirely), and recognizing that requires reframing priorities.  Preferably, focus on customer journeys, and ask if marketing tactics contribute to a better experience.  Consider journeys such as:

 

  • Prospects searching for products to discover and learn more
  • Customers seeking out trials to test those products
  • Customers embarking on a buying or upgrade process
  • Customers doing research on price, available incentives, and financing options
  • People filling out an application, making a booking, or redeeming rewards
  • Consumers getting stuck, struggling, or in need of assistance
  • Clients reaching milestones, entering new life stages, or affected by key events

No organization can serve its customers without supporting people.  To illustrate, assume your kiosk has a reasonable self-service experience, but then something goes wrong.  The technology hiccups, and a customer begins agitating.  Without back-up mechanisms, this situation can quickly turn disastrous.  To avoid it, you need reasonable levels of redundancy, well-tested cut-over processes, and intelligent detectors that gauge the need for human intervention, and then bring the right human into the loop.

Brands that thoughtfully consider these scenarios, elegantly weaving together marketing automation, people, and processes, will deliver better customer experience.

But how can you be sure you’re improving experience?  In short, hyper-focus on one journey at a time, pick metrics to measure each, and correspondingly measure overall satisfaction.  Once more, here’s where many firms trip up.  Instead of measuring whether the customer is fully satisfied with, say, the onboarding journey, they only measure certain tactics, like whether a welcome email got sufficient opens and clicks.

Conclusion

Be honest. We all have some bad habits that admittedly we should give up for our own good.  But breaking old habits isn’t easy.  And like any habits, we’re comfortable with our marketing automation traditions because the outcomes are predictable.  Nonetheless, just because they’re predictable, doesn’t mean they’re best for our customers.

When we force-fit customers into segments, push products on them that we want to sell, confuse them with conflicting and poorly orchestrated channel messages, and hyper-focus on our efficiency (versus their experience), the results will be predictable alright – in other words, we’ll get our anemic 0.5% response rates and slow growth.

If you think, however, you can do better, then take a chance.  Collect as much individualized data as you can, use it to personalize customers’ experiences, coordinate decisions with one principle engagement hub, and as Steve Jobs said, “…start with the customer experience and work backwards to the technology.”

[i] Crossing the chasm: From campaigns to always-on marketing, https://www1.pega.com/insights/resources/crossing-chasm-campaigns-always-marketing , December 2017

[ii] CEB Press Release, https://news.cebglobal.com/press-releases, May 2012

Customers Are INDIVIDUALS Not Averages | How RTIM Treats Them Special

Real-Time Interaction Management (RTIM) delivers personalized experiences to people.

Earlier this year, I signed up for a points program with a large hotel chain, and somehow my last and first name were reversed in the enrollment process.  The next day I noticed the welcome email message started with, “Jeffs, we’re so happy you joined the fam.”  Figuring it was my botch I went online and fixed it in my profile – problem solved – or so I thought.

awesome not averageApparently the erroneous data instantly had spread, like a venomous bite, and propagated to other databases.  My feeble attempt to suck it from the source was too late and didn’t work.  Still, nearly a year later, I still get messages starting with, “Hello, Jeffs” which rather than setting an intimate tone for the oncoming interaction, sets a grating one.  I may still read on, yet I’ve been reminded upfront I’m essentially a bunch of bytes to the interactor on the other end.

I get it – mistakes happen; systems are stitched together, and people (and the systems they use) are under enormous pressures to share data, scale, and automate.  Nonetheless, when firms chose to operate this way – neglecting to fix little things, they’re failing to measure the impact of the most fundamental flaws that often make or break an entire customer relationship.

Traditional Marketing Technology (Martech) vendors espouse solutions allegedly providing personalized communications.  And when their clients deploy these systems, they assume they’ll develop meaningful relationships with individual customers but, the fact is, most won’t.  Customers still routinely report broken processes (like my example), one-size fits all treatments, non-individualized experiences, and very few (only 27 percent) think AI will help.[i]  So, if you’ve been entrusted with helping achieve loyalty-building relationships, that’s more than a little discouraging, since it’s not for lack of will, good intentions, invested time, or resources.

As consumers, we browse, research, shop, and purchase constantly – sharing our information freely (sometimes unbeknownst to us).  We surrender our identity, intentions, preferences, history, location, and so on – often repeatedly, yet we see little in return in terms of well-tailored products, services, and experiences.  And this goes beyond the obvious, such as in self-service experiences (where our expectations for personalization are low), into human-assisted channels where our expectations are higher, but paradoxically we often encounter robotic-like agents.

Consider how brands place customers into huge buckets that dictate treatments:

  • Most loyalty programs have about four tiers. If a program has 10 million members, that’s about 2.5 million members per tier.

 

  • When a data scientist builds a decile-based RFM model (RFM stands for an algorithm that scores based on recent transactions, frequency of them, and their monetary values), that’s 10 segments, and again about 1 million customers per segment.

 

  • And even when zip code level data is used, that’s still about 8,000 people to a segment – and let’s face it, as much as you love your neighbors, you know how different you are from them.

 

Rarely do we enjoy being stereotyped.  When we’re assigned to a troupe, and approve of it, it’s usually because we made a conscious choice.  We find more differences than similarities when we are forced into artificial groupings, and we get rightfully grumpy with being pigeonholed.  Conversely, we rave when companies celebrate our uniqueness, and we love to tell these stories.

 

RTIM – Your AI ROI Machine

AI, arguably the most overused and abused word of the year, particularly among Martech vendors, does have in its midst the underlying technology to begin to solve for improving and individualizing customer experiences, and in techno-geek terms it’s known as RTIM (Real-Time Interaction Management).  Businesspeople using RTIM, however, would rather focus on results versus names, and the reality that these systems consistently generate 300 percent plus ROI [ii] – in other words, they are AI ROI Machines.

Why do RTIM systems outperform traditional marketing automation systems?  Simply put, it’s because they make decisions one individual at a time, hence delivering one-to-one interactions.  Figure 1 depicts the difference between many of today’s Martech systems and an RTIM system:

RTIM

Figure 1 – Typical Martech system versus RTIM system

Figure 1’s top lane depicts how traditional Martech systems place customers into segments, assign offers to those segments, and execute treatments in each channel.  On the other hand, RTIM systems act on behalf of each customer (instead of tranches of them globed into segments).  Moreover, RTIM systems operate based on one set of coordinated rules and analytics linked into a set of arbitration strategies – for thousands of customers per second.

For example, a company with five products marketed by five different divisions uses a single decision engine to resolve the best thing to do for the customer.  Consequently, an RTIM approach enables a brand to act as one organization instead of many disparate companies with dozens of conflicting rule engines.

RTIM-based systems recall an individual’s history – instantaneously – each time a customer interacts, factor in new (contextual) information, and calculate the best action.  They execute real-time analytics to determine an individual’s propensity to respond to a candidate list of eligible offers, then consider customer value and the economic benefits of the offers before rendering a final decision.  Granted, they don’t have perfect knowledge of the person, yet just like a human brain, they remember past interactions and learn from them, and place a premium on the most up-to-date information.  They’re also agile enough to perform dynamic recalculations (in less than one second) to further improve the pending decision and enhance the relationship.  Through this two-way iterative approach, they essentially carry on a real-time conversation in a single session as shown in Figure 2.

Conversational Marketing

Figure 2: RTIM’s iterative two-way conversational approach

Regardless of the superficial popularity and obfuscation of the term AI, it’s incumbent on us as marketing professionals to inspect the value-added by the underlying CX technology.  Earlier this year, Forbes did just that, citing the Forrester Tech Radar on AI technologies, which found decision management as the top hot AI technology (Figure 3).[iii]   And decision management is the central capability embedded in RTIM systems.

With RTIM and its decision management, brands can personalize in real-time, improving on legacy and static Martech systems and processes, and reinvent how customers are treated.   Decision management enables companies to make analytically arbitrated evaluations during every customer contact, treating each person based on their constantly changing context, fluid needs, and demands for relevance and continuity.

In his article, What is RTIM, Barry Levine calls it “Right Now Contextual Marketing” and goes on to cite work by Forrester analysts Rob Bronson and Rusty Warner – who both helped establish RTIM market awareness that culminated in the RTIM Wave[iv].   Levine describes how RTIM enables marketers to perform “a continual negotiation — a kind of dance — happening in real-time between all available data and all available offers/actions.”

AI tech

Figure 3: Forrester AI Tech Radar

Sounds obvious, and aren’t brands already doing this?  Well, not really.  Consider that on many channels:

  • You see the exact same style screen and get messages identical to those of every other visitor.

 

  • You can’t set and store preferences or alerts for receiving communications.

 

  • Call center, branch, and store agents seem ill-equipped to set, store, and recall even the most basic details about you, like how many children or pets you have, and what their names are.

 

  • When you receive an email, it’s maybe one of a handful of different versions, so again, if the brand sending it has a list with millions of email addresses, you’re receiving the same content as thousands of others.

 

  • Advertisements stalk us for products we just bought or already own.

 

  • When you place a call into a service center for the 10th time in 2 weeks (and you’re feeling obligated to invite them to dinner because how much time you’re spending with them), it’s clear the vibe from the agent isn’t exactly a personal one.

 

  • When you start a process on one channel and bail out, and then later reconnect, you’re forced to repeat steps.

 

As marketing practitioners, we can do better.  And as with any road to improvement, it must start with an admission that issues exist and they are negatively impacting others.

 

Impactful Customer Engagement

Great customer engagement starts with customer understanding.  And tiny details matter – things that on the surface seem trivial, although later may turn into a customer testimonial like this:

“Yes, that pet store remembered me, thanked me for my business, remembered my dog’s name breed, and age (Sandy, our Westie, is 14 now). They seemed genuinely concerned for her health and status.  They provided me valuable insights into her dietary considerations, and their app sends me reminders for refills that I might otherwise miss.”

Unpack that and contemplate what it’s implying – a memorable personal experience with an aura of care, empathy, and value.  Remembering names, age, past purchase history, applicable products – admittedly is basic stuff.   But take that basic data, and in combination with other factors, use it to systematically treat each customer’s situation uniquely, and you’ll put information and technology to beneficial use.

So, forget whether this approach is using AI or not, and start worrying about whether what it’s doing makes common sense for your customers at the moment of interaction.  What matters is not whether you store these details, but whether the underlying technology mines that data, learns customer preferences – and with each transaction gets smarter about optimal timing and consumption patterns, and realizes when to trigger meaningful messages.

Frontline staff are already busy, and they’re increasingly asked to be super-human and to provide white-glove treatment at scale.   To do it, they’ll need support from technology that stores and surfaces critical insights at the right time, so they can buck the tendency to treat customers as averages – because, what you don’t want are segment-oriented attitudes like this:

  • Hey since winters coming, everyone needs a coat so we’re pushing winter parkas.
  • She’s one of my older fixed income retiree types – they all love that annuity product.
  • Millennials love iPhones, and tweens always buy that pink Otter case.

 

You want individual-oriented sentiments:

  • That was Jim and he’s 62, and you’d never believe that Jim loves ziplining, has a Shih Tzu, and listens to Dubstep late at night while he reads his email.

 

  • Rosemary says she’ll never retire. She loves her job, loves to day trade, reads email at lunch, and will likely work for her entire life.

 

  • Yes, Sara is a unique. She’s 21 and never responds to text messages, unless from close friends; she gets up early, reads email before work, and is into Hello Kitty, guinea pigs, and Thrash Metal.

 

Each one of your customers are unique people, not customer id’s in cluster codes.  Treat them as such.

Continuous CX Improvement

Back to our little story of the inverted last name.  You’re probably wondering, couldn’t that company have solved this problem without an RTIM system?  Maybe.  But outfits that work from a common customer database, understand the true meaning of “system of record” and synchronize data when its distributed, and use RTIM to operate from an organized set of rules and analytics and make the best possible decisions in the moment are much more likely to consistently get CX right, and to improve it – one person at a time.

[i] What Consumers Really Think About AI: A Global Study, https://www.pega.com/ai-survey, 2017

[ii] Forrester Total Economic Impact (TEI), https://www1.pega.com/insights/resources/forrester-total-economic-impact-tei-pega-marketing, 2016

[iii] Forbes, https://www.forbes.com/sites/gilpress/2017/01/23/top-10-hot-artificial-intelligence-ai-technologies/ , 2017

[iv] The Forrester Wave: Real-Time Interaction Management, https://www.forrester.com/report/The+Forrester+Wave+RealTime+Interaction+Management+Q2+2017/-/E-RES136189, Q2 2017,

What it Takes to be a CX Transformer

Thirty years ago, when I unpacked my first computer, a Commodore 64, rigged it to my 13-inch tube TV, and wrote my first program, the process of creating a digital experience hooked me.  That I could design and assemble mere bits and bytes, package them up into an asset, refine it, and eventually share it for the benefit of others – for entertainment or problem solving – just enthralled me.

CX Transformer

With time and market efficiency sorting who gets paid to do what, I altered my path away from programming and toward design and consulting, leaving the coding and compiling jobs to those more talented than me in that trade. That wonderful feeling of accomplishment, however, never left me and still drives me today.  Whether it’s creating visual concepts, designing software, or producing media, creating a re-usable asset with experiential worth (striving to be a CX transformer), for me, is a universal and time-tested motivator.

Experiential assets, originally made from scratch, must evolve to the liking of their benefactors.  They invariably play a role in nearly every commercial experience.  For example, a vehicle manufacturer produces a physical product, but the agency who markets it as well as the dealer who sells and services it – all add crucial elements into the customer’s journey of shopping for, buying, and owning that vehicle – all contributing to (or subtracting from) accumulated impressions of overall worth and value.

Organizations are either born with this mentality, where it’s baked into the fabric at every level and function of the organization, or they must transform.  Startups who don’t adopt this mentality burn through money and soon dissolve.  Legacy firms are faced with odds not unlike that of a recovering addict.  Most hit bottom, before they realize the extent of their problem, and by then it’s often too late.  Few are afforded the chance to recover and most who try will regress.  In fact, a recent Forrester study [i]indicated as many as 77% of those who embark on CX transformation will fall short.

With all this buzz, don’t we already get great CX?

The short answer is, not really.  According to a global survey [ii]of 7000 consumers, 89% “think brands need to work harder to create a seamless experience for customers.”   There’s lots of talking about seamless and personalized experiences, and less walking the walk.  And consumers continue to report a deficit of it, as evidenced in an Infosys survey [iii]indicating that 73% have never experienced online personalization.  Here’s the reason:  Many of us, and the firms we work for, aren’t practicing what we preach.

Regardless of what you do, you’re in the business of creating customer experiences.  Whether in sales, marketing, service, or operations; whether you set vision, do design work, code, implement, consult, or the like, your ultimate mission is creating something that someone else appreciates and finds value in – because it makes their life better.  It improves their experience.  If you can’t tie what you do and why you do it back to that, your mission is misdirected.

The only reason customers buy, use, or recommend products or services is because they experience value.  So, if you simply blabber about CX but don’t improve it, you’re subtracting value, like in figure 1:

CX Talk vs Walk

Figure 1: All Talk Equals Value-Subtracted from CX

Everyone plays a role in experience management.  For example:

  • If you’re a banker, during any interaction, clients are judging each aspect of your services. When they point out friction, dissatisfaction, annoyances, frustrations – they aren’t being pests – they’re handing you gold.
  • If you manage a telco’s call center, though one step removed from direct feedback, front-line agents will hand you that gold. Will you ignore it, or will you investigate, catalog it, document it, and act on it?
  • If you design software used by that banker or agent, you’re instrumental to how the total experience comes off when moments of customer truth occur. Software augments customer facing CX delivery, either enhancing it or contributing to its malfunctions.

Software and AI technologies have already changed our lives, and continue to transform how we experience life.  From when we wake to the minute we doze off, the way we interact with the world, for business and pleasure, is vastly different now from the day I cracked open that Commodore box.

Data is abundant and the right intelligence in software is available. Yet how both are captured and deployed is what spells the difference between memorable moments versus forgettable incidents.  Dated advice, cloaked as sage recommendations, abounds on what data to tap and which AI technologies to trust.

Beware of the CRM “Catchers in the Rye” who have a vested interest in selling old software disguised as AI and one-to-one personalization, spruced up with fancy new names like Customer Data Platforms, but stuck in a forgone era. Peel these back and see if they rest on an old batch and blast architectures with no real proven use cases for predictive analytics, built essentially for pushing emails to segments.  You’re sure to hit a wall with these, since they were never built to handle real-time, analytics based one-to-one contextual engagements. If you’re interested, I cover this topic in more depth in this article.

Or worse still, beware the do-it-yourself CRM & AI pushers, selling piles of new programming gadgets with exotic names such as Python, Storm, Spark, and Kafka, but missing the warning label that says, “Much assembly required.”

CX Transformation Process

The transformation process, contrary to overhyped tales of sudden disruption, is mostly evolutionary.  It involves creative minds with an unwavering and relentless obsession to improve experiences – as measured by customers.  But today you must do everything you can to go through this process fast.

Iteration (figuring out how to improve) means executing various steps in succession – speedily and repeatedly to learn fast.  It also takes a flexible methodology and tools supporting rapid revisions.  Each time Thomas Edison’s filament didn’t work, he wasn’t failing, he was learning.  When asked about racking up so many failures, Edison replied, “I have not failed 10,000 times. I have not failed once. I have succeeded in proving that those 10,000 ways will not work. When I have eliminated the ways that will not work, I will find the way that will work.”

Be unyielding in finding gaps, filling needs, overcoming shortcoming, and plugging them with an improved asset.  Find the simple stuff, that exacerbates customers, but is easily addressed.  Do ten thousand little things right – and fast.

To succeed, you’ll need to be well-equipped with the right CX transformation methodology and technology. Speed to market and economies of scale matter now more than ever.  It takes steadfast customer centric vision, modern tooling, and an agile methodology.  Let’s explore the four key steps shown in figure 2.

CX Transformer

Figure 2: Depicting the CX transformational process steps

 

 

CX Transformer Step #1: Conceive Innovation

As you come up with a concept, consider the objectives…. making things better, faster, cheaper.  Ideally, you’ll eventually address all these, but practically you’ll need focus. Will the proposed innovation fix something that is terribly broken?  Better yet, will it preemptively address a shortcoming.  Often, fixing inadequacies is simple, yet the consequences of not fixing them are huge.

To find opportunities for CX innovations, use analytic heatmaps fed by behavior data on websites and mobile devices to zero in on where customers struggle or bail out.  Mine reviews, comments, call logs to find repeating themes.

Here’s an example I heard from a person I sat next to on a flight.  He had booked a trip to Dubai, but the travel service never proactively alerted him that travel to UAE requires a passport that doesn’t expire in less than six months.  On his departure day, he couldn’t check in, and subsequently was on the phone for hours, working the problem and seeking amends for this horrible experience.  The root cause was recorded in logs. The fix (innovation if you will) was rudimentary and excruciatingly easy.

“If customer books trip to country X, and passport expiration date is Y, alert customer about passport rule.”

In this case, the customer placed a gold nugget into the lap of the brand, begging them to fix it for future customers.  Will they?  Only if they’ve institutionalized collecting hiccups like this, and weaving them into the innovation and improvement process.

Think of innovations in sets.  Will the CX innovation set be press-worthy; will the total experience be unique and better?  Take the innovation set and break it down into manageable chunks. To improve service usability, for example, consider whether the specific design is elegant, visually appealing, modern, stylistic, easily navigated, intuitive, and so forth.  Remember, even when just creating a form, such as an insurance policy application, all the above matters in CX.

Spend three times as much effort on design versus construction.  If service improvement is your aim, pick (as your innovation set) a critical customer journey that cuts across various functions and channels, and obsess with its design. While iterating on the design, always apply a range of customer sniff tests tied to customer personas.  How would customer X use this?  How would customer Y perceive this?

Just as incentive drives employee behavior, it drives customer behavior.  Customers are motivated by the value they both perceive and achieve from using your products and services, regardless of the organizational excuses they encounter along the way.

CX Transformer Step #2: Judge Harshly

Critique innovations, not just with self-criticism, but with the varied feedback of others. Compare to market alternatives and what big competitors are doing and what customers complain about.  Once again, view the current state of the experience through customer eyes.  Clients not only measure success, they also give clues about required innovations.  If an asset works they use it, open it, share it, like it, and buy it.

Watch exactly how customers use the innovation.  Designers call this usability testing, and too often, it’s shortcut out of the development process in the name of speed.  Watch how customers interact, how they shop, how they decide, whom they consult with, and why they buy.  Look for where they struggle, the questions they ask, why they need help, and ask what went wrong. Then go back to the drawing board to create a new experience, craft a new email, create a form, redesign a web page, or work on ideas to improve how agents engage with customers.

Use a basic four quadrant Risk / Reward matrix, as shown in figure 3, to prioritize a backlog of CX improvement opportunities.

Value Matrix

Figure 3: Risk (Effort) / Reward (Value) matrix used to prioritize innovation ideas

Don’t make your goal mimicking competitors, but instead to gauge your inferiorities to them, study their winning ways, and chart your course –  but dare to be different – then test and learn.  Compare your asset to others available in market.  This guides, both in terms of whether you’re behind, but also what hasn’t been done – thus presenting opportunities to do something new, something unique.

Pattern yourself on proven winners, not just in your industry, but also in very different ones.  Why?  Because that’s where unique ideas come from – not from copying your competitors, but from proxies that when applied to a different problem become a new idea.

For instance, to transform the branch experience for its customers, Capital One recently introduced café style locations, drawing on a combination of Starbucks and Apple store concepts.

CX Transformer Step #3: Apply a Value Test

Determine whether your innovations improve experience. To do this, perform behavior tests and not just surveys.  People don’t always do what they say they’ll do.  Test your innovation by getting real customers to use it in production pilots, and then measure whether, for instance, the task was accomplished faster.

Getting there may not be easy, cheap, or fast, but if your product isn’t passing these tests, you haven’t improved your customer’s experience.  Each innovation should pass at least one of these tests, and collectively overtime, it must pass all three.

At this stage, the test is if your customers are buying or using your asset.  If they see value, they’ll do these things, so measure for it, and use this as your ultimate yardstick.

CX Transformer Step #4: Analyze Objectively

Once you release your concept into the memorialized world of production, objectively (and recurrently) evaluate its worth.  What works today may not work tomorrow. In addition to pure customer feedback, consider getting an objective third party to scrutinize it, since creators as well as customers have blind spots and biased views.

For all its advances, and there are many, CX today – when analyzed objectively – is still mostly choppy, dysfunctional, too slow, and places too much burden on the customer.  Admittedly, some industries (such as banking and telecommunications) have made more progress than others, yet largely, especially for massive enterprises, CX is frankly still very siloed.

Firms spend millions of dollars on data collection, design thinking, journey mapping, voice of customer, CRM systems, employee training, and so on.  Yet when these efforts are not coordinated around a systematic process, data, technology, and culture – hyper coordinated and committed to improving CX –most of that investment will be for naught.

It’s human nature to either ignore feedback or want to defend your baby’s looks, and if you’re busy defending versus fixing simple things, CX won’t improve much.  It’s also human nature to pass the buck – meaning no one will take responsibility, because even though at our core we’re pack animals, it’s ironically not in our nature to communicate issues across organizational pillars.

CX transformation doesn’t come easy and it doesn’t come cheap, and rarely comes fast.  But for those who listen to and watch customers, fix ten thousand small things fast, live by the adage innovate or die, and cross-functionally collaborate on behalf of better customer experience, the rewards will be plenty.

[i] Forrester, http://www.datastax.com/wp-content/uploads/resources/whitepaper/Forrester-CX-TLP_DataStax.pdf, April 2017

[ii] Zendesk,  http://d16cvnquvjw7pr.cloudfront.net/resources/whitepapers/Omnichannel-Customer-Service-Gap.pdf, November 2013

[iii] Infosys, https://www.infosys.com/newsroom/press-releases/Documents/genome-research-report.pdf, 2013

Machines Won’t Take Over…But A Few AI Titans Might

Lately, if you’re like me and enjoy following the AI narrative (even if just for grins & giggles), you’re inevitably sucked into philosophical wormholes that always seem to pop you out at the same place – a world where machines rule all.

AI titans
Tech Titans

Strangely, though, we rarely encounter future scenarios that follow a path we’re already on, where machines are but tools used to assist us. If we project this scene forward, some interesting questions to ask are, “What does that world look like, and who are its haves and have-nots?  Are AI titans forming?”

AI, for all its hype and promise, is still very much in its infancy.  Far from being able to get up, put on its clothes, and take your job, AI today is less of a super scary robot, and more like a smart washing machine (funny you should ask, as there is one of those).  It can help us conserve resources and do specialized tasks more efficiently, like getting clothes clean using fewer resources, but it really can’t do higher order thinking we take for granted like abstract judgement and reasoning. However, that super smart washing machine (and all its other specialized variants) has an owner, and together they can wield tremendous influence.  And anti-trust laws (put in place over 100 years ago to prevent corporate behemoths from controlling entire markets) may be full of loop holes in the digital age.

Using a singularity argument where machines alone rule provides a convenient escape from a more complex debate about a future where various human and machine forces collide and collapse together.  In this scenario, a select set of firms use walled garden data to feed their AI, and as such, seize unprecedented levels of control, influence, and power.

Here’s an example.  We’re already seeing a massive rationalization of power and influence collapsing into AI titans like Google, Facebook, Apple, Microsoft, and Amazon (controlled by surprisingly few individuals); not pure machines, but formidable entities nonetheless, fueled by AI, and directed by small pools of mighty people already circling their wagons around a plethora of data.

In the short run, we (the consumers) seem to benefit, getting innovative little features and conveniences such as travel guidance and digital yellow pages, but unbeknownst to most, to get these we sacrifice gobs of data and hence privacy.  Each time we travel with GPS on, our whereabouts are tracked and stored.  Each time we search, we provide preference footprints.  Meanwhile, the behemoths rack the data up, building behavior and preference repositories on each of us.

So what’s the rub?

First, it’s our data.  Thus, it would be nice to be able to view it, and if it’s wrong, correct it.  The European Union passed a law recently that goes into effect in May 2018 called GDPR – General Data Protection Regulation.  Its intent is to give consumers more rights and transparency with their digital data.  Other consumers outside the EU could use similar privacy protection laws.

Second, to some extent, without being cognizant of it, our choices are already being limited.  For example, when you search in digital maps, perform online comparison-shopping, or ask a voice pod for restaurant recommendations, the top options returned may not be calculated objectively.  Ranking algorithms already place higher emphasis on businesses that pay more to play, and search conglomerates, like Google, rank their interests (including businesses they have a stake in) higher.

Each time we purchase something, we’re casting a vote.  When we go through a buying cycle, we are creating implied demand, and when we purchase we’re reinforcing that the supply is meeting the demand we created. When this cycle is cornered, choice becomes an illusion.  To illustrate, on June 27, 2017 the EU slapped Google with a record-breaking $2.7 billion fine, charging the tech titan with doctoring search results giving an “illegal advantage” to its interests while harming its rivals.

Third, firms can and will use your data for their benefit, and not necessarily yours.  Prior to the digital age, people stereotyped others by their physical choices such as their house, car, job, shopping habits, and clothes.  Although today those choices still factor in, we also project digital personas: where we surf, what we share and like on Facebook and Instagram, what devices and channels we use, how we interact online, and so forth.  When these behaviors are crunched and codified, they become rich fuel for algorithms that can manipulate, discriminate, or even do harm, without the algorithm’s owners having any concerns for side or after effects.  Show preference for fast cars and thrill-seeking vacations, and not only will you receive more of those offers, but you might also receive higher insurance premiums.  Share enough medical history, and an insurer’s algorithm may score you at high risk for a chronic disease, even when there’s no medical diagnosis, and there’s no certainty you’ll ever develop that condition.  That might make it very hard to get medical coverage.

Admittedly, not all of the use cases lead to undesirable outcomes.  In late 2016, American Banker ran an article on next-gen biometrics detailing how banks use consumer digital behavior signatures to detect fraud and protect consumers from its effects.  And although consumers initially do benefit from such a service, what’s interesting (and concerning) is the nature of the behavior data fed to the fraud detection algorithm:  the angle at which the operator typically holds the smartphone, pressure levels on the touch screen, and cadence of keystrokes.

Unquestionably, the bank’s primary goal is predicting whether an imposter is behind the device in question.  Nonetheless, what’s stopping this same bank from using that data to predict a consumer’s likely mental state, such as likelihood of inebriation, legal or otherwise?  Moreover, whether that prediction is ultimately accurate is irrelevant to the immediate recommended action and the subsequent consequences.  We have little protection from the effects of algorithmic false positives, and today, except for credit scores, few brands have any accountability for model scoring accuracy.

Here’s a scenario.  An algorithm thinks you’ve been drinking based on your smartphone behavior and flags you as too drunk to drive and disables your car, forcing you to find another way home.  That’s one thing, but think about this – that same data might also be available to prospective employers, who use it to forecast your job performance, scoring you lower than other candidates based on its dubious drug use prediction.

Who owns and manages your digital behavior data?  Are they subject to use restrictions? The answer is (although the data is about your profile and your behavior) – you don’t own it and your rights are limited. And although some of the more inconsequential data is scattered about (such as name, address, date of birth, and so on), the deeper behavioral insights are amassed, stored, and crunched by the AI titans, with seemingly no limits or full transparency, and with little insight into where its shipped, and who else might eventually use it.  They suggest we simply trust them.

Those that ignore history are doomed to repeat it

History is always an amazing teacher.  In the 19th century, railroads consolidated into monopolies that controlled the fate of other expanding industries, such as iron, steel, and oil.  They dominated the distribution infrastructure – just as today’s AI titans, in many respects, control the lifeblood of modern day companies – their prospect and customer traffic.  And those other expanding industries (iron, steel, oil) were no different.  They too controlled the fate of other expanding industries, which all needed their materials.

Soon after their start, Google’s founders adopted a mantra, “Don’t be evil.”  In October 2015, under the new parent company Alphabet, that changed to “Do the right thing.”  Although the revised phrase still rings with the implication of justice, it raises the question of who benefits from that justice, and if there’s a disguised internal trust forming.

Everyone knows that business, by its very nature, is profit driven.  There’s nothing wrong with that, yet history teaches us that we need checks and balances to promote a level playing field for other competitors or potential entrants, and for consumers.

History Lesson

In his 1998 book “The Meaning of it All,” Richard Feynman, a famous scientist, tells a story of entering a Buddhist temple and encountering a man giving sage advice.  He said, “To every man is given the key to the gates of heaven. The same key opens the gates of hell.”  Unpacked and applied to AI today:

  1. The term “every man” can imply an individual, or organization made of people, or humankind as a whole.
  2. Science, technology, data, and artificial intelligence are but tools. As history shows, humans use them for good and evil purposes.
  3. AI’s impact on the future isn’t pre-determined. Each of us can play a role in shaping how it turns out.

Let’s ensure we live in a world where many (not a select few) benefit from AI’s capacity and ability to improve lives, and that those responsible for its development, evolution, and application are held to fair and ethical standards.

Can AI be the rising tide that lifts all boats?

The power and potential of artificial intelligence technologies is clear, yet our ability to control it, and deploy it sustainably is not.  Who should regulate and control it (and its fuel- our data) is an evolving and ongoing debate.

Used responsibly and applied democratically, we all stand to benefit from AI.  Paradoxically, while it renders some of our old jobs obsolete, it retrains us for a new world where it and we play new and more rewarding roles – where living standards rise and mortality rates fall.

What’s our guarantee we’re marching toward that future?

Honestly, there are no guarantees – our world is devoid of certainty.  However, we can influence likely outcomes by advocating for practical checks and balances.  Call me a dreamer, but I envision a world where our privacy is valued and respected.  Where we better understand the value of our data and get a reasonable exchange in return when we share it. Where we appreciate what happens when we release it, and can hold those accountable that illegally mangle or pawn it; and a world where we have assurance that when we share data, others uphold their end of the agreement, and we have recourse if they don’t.

If you would like to continue contemplating some of the top ethical implications of AI’s evolving story, click on this link:

https://www.weforum.org/agenda/2016/10/top-10-ethical-issues-in-artificial-intelligence/

Here’s my favorite quote from it:

“If we succeed with the transition, one day we might look back and think that it was barbaric that human beings were required to sell the majority of their waking time just to be able to live.”

Peace

Are CX pros guilty of brain hacking?

Brain Hacking

If you have a smartphone, laptop, tablet, or all of the above, it’s no longer a question if you’re addicted to being online, it’s a question if you recognize the problem and are in control of it.  And if you don’t have any of these devices, I’d love to meet you and even shake your hand (since you’ll actually have one free) – before you become extinct that is, since your breed is already on the brink.

Why are we so addicted to technology?  Perhaps there isn’t one simple answer, but an emerging hypothesis mainstreamed recently when CBS ran a segment on 60 minutes titled “Brain Hacking.”  If you haven’t seen it, it’s worth a watch.  Not surprisingly, yet ironically, to get to the replay, CBS forces you to watch ads.

In the segment, Tristan Harris, a former Google employee, refers to our digital devices as slot machines, and in a recent blog claims, “…technology hijacks people’s minds.”  Ramsey Brown, co-founder of Dopamine Labs, calls the developers responsible for making the apps we use everyday “brain hackers” – essentially meaning they employ techniques designed to get us hooked and to alter our behavior.  Arguably, these ubiquitous methods have already succeeded in causing habitual behavior.  And if you’re not convinced, unglue your eyes for a moment from your device du jour, peer up, and notice everyone else’s heads buried in digital appliances, and how antsy they’ll get when unplugged for only a few minutes.

Essentially in concept, it’s similar to a virus invading the body (hence the hacking metaphor), with its mission to reprogram us to crave constant online activity.  Behind each antigen are hackers, engaged in a form of biological warfare, engineering their payloads to infect our brains to crave more activity – on their sites and apps.  Though it’s debatable how much of the altered conduct can be directly attributed to just a few hackers, the pervasiveness of the behavior is indisputable.

Race to the bottom of the brain stem

Tristan refers to this battle as a “race to the bottom of the brain stem,” implying these cerebral hackers are sparring for our attention, and will do anything to get more of it by appealing to a range of our human needs, even the most primitive ones.

So, are all CX pros guilty of this practice, or just a select few in Silicon Valley?  In terms of marketing techniques, is this something new or merely old methods with new names?

Perhaps guilty isn’t the fairest word (with its implication of wrongdoing), but I’ll posit the first answer is yes, most professionals tasked with generating demand are trying to do this – with the huge caveat that some think (operative word “think”) they are close to solving an ageless puzzle of how each human mind operates and how to manipulate it.  Further, it’s not the impact of a few, but instead the collective efforts of many demand generators, as well as our growing dependence on technology, that’s contributing to our hyperactive online behavior.

Nevertheless, today only a few dominant firms enjoy the majority of the economic rewards, since users spend the majority of their online time in select applications such as Facebook and Google.  Call this the tech titan factor, a few gargantuan companies controlling the vast majority of user interactions that attract eyeballs to digital advertisements.

As for the novelty of this approach, the core practice is actually as old as direct marketing itself.  Like doctors, trained direct marketers learn early on that diagnosis, problem understanding, and treatments followed by continuous application of test & learn methodology, are time-honored principles proven to attract attention and optimize engagement.  What’s changed are the tools CX pros have to administer continuous and tailored therapies (see my article on the use of Prescriptive AI in CX), and as consumers how we’ve unknowingly given up more data about ourselves and increased the quantity of our online intake.  Further, this medication being administered to us comes with no warning labels or explicit documentation as to the harmful side effects.

In terms of affecting consumer consciousness and behavior, marketers have again followed long-standing hard and fast principles.  Take Maslow’s hierarchy of needs:

Maslows Needs

The reward consumers get from checking their devices depends on the individual’s specific needs.  For instance, one person may be in the pursuit of self-actualization, and as such may be constantly using a gadget for educational discovery.  Another may be in search of esteem, and becomes hooked on social media in a constant quest for recognition.  No matter the reason for being online, advertisers track, analyze, and subsequently prescribe remedies squarely aimed at selling us goods and services they’ve ascertained we need.

Moreover, take the streaks tactic that Snapchat uses.  This is simply age-old marketing gamification at work.   It’s true today’s games are digital, more dynamic, mobile, and played by all ages, but S&H had consumers playing very similar marketing games in the 1930’s, with the goal of creating green stamp junkies.

Whether a modern game, or a game from the 1930’s, the basics of this approach are similar.  Entice someone to play but don’t let them win out (making the game incremental – in this case the increment is days), luring them back in, and make the game length seemingly infinite (e.g., collect stamps; cash them in; collect more).

The persuasive fight for our attention

Have newly minted CX pros devised new sinister methods of mind control?  Has a new economy suddenly emerged centered on getting attention at all costs, hooking people into using products? I don’t think so.

As far back as the 1950’s, fears about mind control perpetrated by marketers were already spreading, and various theories, many of them hoaxes, began to crop up.  And the commercialization of everything, from historical sites to holidays, can be traced back to right after the American Civil War.

In the late 1950’s, rumors abounded such as stories of theaters lacing film with stealthily implanted single frames of subliminal messages such as “Eat Popcorn” and “Drink Coke” supposedly engineered to stimulate instantaneous demand for these products.   In 1957, Vance Packard wrote a groundbreaking novel titled, “The Hidden Persuaders,” making an original argument that organizations are born to manipulate, and had moved from overt tactics to clandestine ones, with hired agencies as the evil genius behind it all.  Quite possibly the only difference today is that we carry around in our pockets millions of commercials, and check in constantly, making us continuous targets for impressions.  Unscrupulous marketers, as well as those with shreds of decency, have existed side by side since the dawn of time.  They simply have more access (by virtue of over 150 years of marketing, commercial, and technological evolution) to more minutes of our waking attention, and will always vie for a slice of that bandwidth with newfangled material engineered to break through the clutter.

When you reflect on it, marketers seek attention and puff their wares – it’s what they do.   How and where they’ve sought it and how much they’ve puffed has always defined the extent to which they further commercialize our environment and how far they push ethical and legal boundaries.

This fight to own a share of our precious attention itself contributes to a further lack of focus and increased distraction.  I wrote a related piece on this (Contextual Incremental Marketing), from the point of view of the marketer, at the time not fully grasping that my tips about the phenomena were in fact recursive, that is, further reinforcing and encouraging the behaviors that I suggested were simply a facet of the modern world.

In a sense, it’s a vicious circle, but not a new one:  CX pros stalking consumers, contending for their attention via an ever-exploding channel continuum, employing any means to engage their reptilian brain and interrupt them, persuade them, adding to attention deficit disorder.  For consumers, the antidote is the same as it ever was – common sense, education (with reliable and readily available sources of accurate information), balance and moderation, free will, and self-control.

The surveillance economy

Like crime scene investigators (for more on this, read my blog: The CSI Guy – Customer Success Investigator), CX pros seek clues to solve the mysteries of making best guesses about the likely behavior, needs, and actions of customers.

Those involved in pure acquisition have little to go by, and as such, stretch for data and surveillance methods, test data privacy, ethical, and permission boundaries, and often still miss the relevance mark.  In many respects, they are like matchmakers, casting a wide net, and hoping to bring in a few choice prospects.  Those tasked with building on relationships, often called relationship or loyalty marketers, have it easier, with a treasure trove of owned media behavior data at their fingertips collected by modern digital tracking sensors.  In either case, it should come as no surprise that gathering evidence is a top priority.

In 1992, Eric Lawson wrote a book called “The Naked Consumer.”  It was an excellent account of the growing problem at the time of personal data sold as a commodity on the open market, and its lessons and conclusions are as germane as ever.

 

So what should we do?

Like any history, there always seems to be the appearance of it repeating itself, but invariably with evolving twists.  In this case, some of the twists are:

  • We can take devices with games and reinforcements anywhere, and often do. Mobility means more chances to be online.  In contrast, when TVs first appeared, they were stationary.  And radios were too bulky to carry, until transistors transformed them into the iPod of the 50’s.

 

  • Because this digital drug is available constantly, and there are no official regulators, many of us are unconsciously overindulging. Like any addiction, step one is problem recognition, and for most of us, we haven’t admitted there’s a problem, let alone embarked on a recovery journey.

 

  • For digital natives (those who have grown up with smartphones and social media), there are new pressures and social dynamics many of us that are older can’t fully appreciate. This has resulted in massive numbers of teens afflicted with anxiety and depression (see this Time Magazine article for an in-depth look). That’s sad.  There’s no easy answers, as these issues are rooted not only in technological realities, but interwoven with deep seeded tribal sociological phenomena.

 

  • Impatience thresholds are down to seconds, partly due to the availability of technology itself and our dependence on it, and on industrial productivity pressures.

 

What should CX pros do?

There’s no disputing that businesses need customers and have to make money to survive.   How they play the game, the rules they follow, and the cultural approach they use defines both their character and destiny.  When plotting how to engage customers with artificial intelligence and automation technology, consider the following:

  • Those who play the long game win the long game. If the ultimate goal is improving customer experience, then factor customer quality of life into the long-term value equation.  Depending on the definition and time horizon for winning, chances are good consumers will recognize (and reward) you for considering their best interests.

 

  • Regulate, or be regulated. Incidentally, industry in general doesn’t have a great track record for self-regulation, so prepare eventually for some regulations in this area to emerge.

 

What should consumers do?

Throughout recorded history, hucksters have been selling unsuspecting consumers products they really didn’t need.  That doesn’t mean every modern day CX pro inherits the label of huckster.

Quite the contrary, those who exchange value with consumers, and provide them with solid recommendations of products well suited to their requirements are effectively service providers.  Those taking the easy path and simply pushing and deceiving others toward a clever sale, will rightfully earn the dubious timeworn label.

Consumers need to:

  • Shop around. Although it can be a hassle, weigh the pros & cons of moving to another provider, versus amassing more points or transactions with a single provider.   Be sure, nonetheless, to factor in all switching costs, including your time.

 

  • When you shop, think outside the box to get a list of alternatives. The path of least resistance these days is to search on Google, but that list of both the paid results as well as the first page of organic ones is a limited (and often highly biased) set.

 

  • Take occasional breaks from technology – Simply put, you don’t need to be online every minute. Don’t expect to completely kick the habit, same as you can’t stop eating food altogether. Research already shows, however, you should use technology in moderation or your long-term health may be at stake.  A recent survey of 3500 adults shows stress levels likely rise when alerts go off, such as new emails or text messages. Like getting adequate sleep is necessary for good health, you’ll probably be more productive (and live a longer, heathier life) if you’re offline periodically.

 

Event-based marketing (EBM) & CEP use cases for CRM

Updated: February 3, 2020

Introduction – The Key Event Types

First, check out my latest article on this topic recently published: Shush – Listen for customer signals with event-based marketing & service —- Out of that article surfaced these distinct event categories:
Event Category Example
Account status Average bank account balance trending down (by X standard deviations)
Behavior-Account Roaming charges incurred or within x% of the limit
Behavior-Device Failure of device/machine
Behavior-Person Digital browsing – showing purchase interest/intent
Calendar Major shopping holiday approaching
Contract-Account Changes in the account/contract terms & conditions
Environmental Severe weather alert – hurricane warning
Forecast Model score updated – Churn/attrition score rises above a threshold
Inactivity No activity (of a certain type) in the last 30 days – e.g., no deposits
Law/regulation Change in the overall privacy policy
Milestone Birthday – Age changes (milestones such as 18, 55, 65, etc.)
Product/Service Replenish – consumable products, such as printer ink
Product-wide/Service-wide The interest rate on all accounts of type X increases by x%
Profile-Person Investable assets increase (or decrease) by x% (or crosses a threshold)
Transaction status Order status change (disruption in availability, timing)
Below you’ll find an inventory of event-based marketing (EBM) and complex event processing (CEP) use cases for customer experience management.  In each, the system senses behavior and alerts a user or another system to the unusual activities or conditions that warrant further investigation or action.

Vertical Complex Event Processing Use Cases

Fiserv: Consumer Banking and Credit Cards

  • Unusual account activity (e.g., large deposits/withdraws)
  • Unusual account activity trend (e.g., average daily balance down by two standard deviations)
  • Inactivity pattern (e.g., no transactions in last week)
  • Missed transaction (e.g., missed direct deposit)
  • Credit card spend activity use pattern (by spending category)
  • Insufficient funds pattern
  • Web or mobile click activity indicating an interest in a product

Insurance

  • Fraudulent claims activity

Operations

  • Predictive maintenance systems

Media and Communications

  • Dropped call pattern or degradation of signal/service
  • A customer has increased roaming (or other unusual account usages) behavior
  • Customer in route to a foreign country pattern
  • Popular programming based on a set-top box and social media insights
  • Prepaid consumption detection and stimulation
  • Churn detection

Healthcare

  • Claims fraud
  • Care interruption pattern
  • Fitness monitoring
  • Hygiene procedures pattern
  • Healthcare patient monitoring

Horizontal Complex Event Processing Use Cases

Customer Service Center / Retention Department / Loyalty

  • Customer struggling to get help pattern
  • Payment due
  • Strange returns activity
  • Customer likely wants to cancel service
  • Customer’s birthday
  • Customer’s service anniversary (e.g., been a customer for X years)

Marketing / Cross-sell & Up-sell

  • Customer online interest in a product or service
  • Customer in store interest in a product or service
  • Customer in the proximity of a store
  • Customer usage stimulation – Drop off in use of a product/service
  • Increase in use of a product/service
  • Loyalty Program – Monitoring points activity
  • Loyalty Program – Monitoring points expiration date
  • Monitoring social sentiment
  • Monitoring social influencer

Non-CX use cases

Here are some examples that are not for CX, but instead to improve business and operations efficiency:
  • Algorithmic stock trading such as if Stock A rises by X% and Stock B doesn’t automatically buy Stock B
  • Transportation security and fraud detection such as an id card used twice in a short time frame (e.g., piggybacking) or high volume transactions on a new account – and then automatically alerting the right parties
  • Detecting transportation congestion and incidents, and proactive notification of alternative routes
  • Inferred detections suggesting that a vehicle has crashed (and severity of crash), such as when an airbag has deployed
  • Communications security such as false alarms going off in a certain time window, not followed by other alarms that would be expected (false positive alarming)
  • Communications security such as network monitoring for detecting denial of service attacks, and alerting the right parties of this situation

Marketing Wish List – “All I want for the holidays”

In my series on Customer Data & Decisions, I’ve explored how marketers covet that prized asset a “360 Customer View.”  In this blog, I turn things around, viewing from the consumer’s eyes what’s expected from marketing today, in the form of a marketing wish list.

Marketing Wish List

The Final Countdown – A consumer’s holiday wish list for marketing

Hello Marketing, I’ve been thinking about my wish list for the holidays.   Like a kid in a candy shop, here it is:

  1. First and foremost, please make sure your company builds great product and services. I don’t care how well you wrap the present, or how much money you spend on the wrapping paper.  I care about the present inside, and whether it’s useful to me.
  2. Once you’re sure you have a great present inside, go ahead and tell me all about it. I don’t mind hearing your passionate stories about how great it is, if it’s really great.  But don’t take too long to do it because I’m busy and you won’t have my attention for long.  While you have my attention, feel free to entertain me.  I like that aspect of marketing.
  3. Oh, and by the way, before you decide on this great present for me, make a reasonable effort to figure out why I’m possibly interested in it. Once you do that, then and only then, direct your clever marketing at me.
  4. Maybe I don’t know I need your present. Fine, so tell me quickly and concisely why I need it, and what unique value it will bring to my life.
  5. When you decide to tell me you have a present for me, don’t expect me to work miracles finding out about it. Make a reasonable effort to figure out where I spend my time.  Marketing, I know you are like a modern Santa, with access to all kinds of big data on my every move that gives you real-time information on whether I’m sleeping or awake; my exact location at all times, etc. – so use it wisely.
  6. Take notice to when I pay attention to your marketing – what’s working for me and what isn’t, and learn from that. Like a comedian knows, timing is everything.  If I’m not clicking or I’m not laughing, then ditch the joke.
  7. FinalCountdownOnce you get my attention, treat that moment like we were potential friends meeting for the first time. If you’re interesting, friendly, and we have things in common, we will probably want to meet again.   So treat our relationship accordingly.   Make an effort to get to know me before you try to close me.   Marketing gets a bad name from “ABC – Always-Be-Closing” selling.
  8. Basically, don’t sell to me, help me buy. Point me to helpful information that demonstrates your present has value, will last, is fairly priced, and that others I’ll trust love it also.  If you are offering me something special, make sure there is a good reason for it being “special for me.”
  9. If I’ve told you or given you obvious clues that it’s not the “Greatest Gift Ever”, respect that. In other words, don’t sell beyond the “Really I’m Not Interested Now”. If I didn’t tell you why I’m not interested – you can ask me – but whatever answer I give honor it.  Don’t push any further.  After all, just as bad as me not taking your gift, is me accepting it and later telling others how useless it was and re-gifting it because I really didn’t like or need it.
  10. Microwave at 10 secAnd finally, Santa, can you please take 15 minutes or less and talk with that Gecko Company and ask them to spend – I don’t know maybe 15% less on mass advertising next year? I just can’t get that Song “The Final Countdown” out of my head.  On second thought, never mind, I know what they will say: “If you are a Mass Marketer, you spend big bucks to get inside heads….it’s what you do.”

For interesting further related reading, and reflection on the year 2015, read “The 2015 Marketing Wish List” at http://www.dmnews.com/marketing-strategy/the-2015-marketing-wish-list/article/387692/

Comments and alternative views are always welcomed.

Note:  These views are my own, and not that of my employer

The CSI Guy – Customer Success Investigator

sherlockRecently I read a fascinating article on how crime investigators are using machine learning to find patterns and uncover insights that otherwise wouldn’t be detectable.   Investigations ranged from criminal to cybersecurity, competitive counterintelligence, and corporate litigation.  In one example, a firm showcased how – if this technology had been available during the Enron era – they might have proactively detected the scandal, potentially averting the crisis.  Their demo traversed 500,000 Enron emails, and as it did it learned how to flag suspicious ones.

It’s not news that pattern detection software works for fraud detection.   For years, banks have employed systems that scan structured credit card transaction data, and flag unusual activity.  Yet what occurred to me is this same approach and its specific techniques are extremely well suited to the art and science of developing customer intelligence against unstructured big data.   Customer experience pros could then unlock new mysteries, and take appropriate actions leading to great customer success outcomes.

The first thing criminal investigators do is they gather all the facts they can, from any available source – Emails, phone records, texts, web activity.  The adage being “Leave no stone unturned.”   It’s never clear at the start of any investigation which clues might matter, and may link to others – so all are important regardless of their form.    As the investigation unfolds, machine learning techniques, such as neural networks that use self-organizing cluster maps (known as SOMs) can help find patterns, and eventually help the investigators form a hypothesis.  Available evidence is used to test whether the facts fit the theory.

Shifting the frame of reference, gaining customer intelligence and using it to solve for marketing and customer experience challenges can benefit from this same methodology and technology:

  • Consumers leave clues about their preferences and behavior in many places; sometimes in unstructured forums, like social media, product reviews, and blogs.
  • It’s virtually impossible to sift through this data without the aid of technology and automation.
  • Machine learning can be used to find patterns in customer activity, such as what product they are most interested in buying, or that their sentiment is trending toward total dissatisfaction.
  • Once patterns are detected, predictions can be made and actions triggered in efforts to anticipate needs or alleviate matters.

As a consumer, my natural reaction might be to say, “That’s creepy and spooky”.   Ironically though, most firms simply want to use this to improve your experience with their brands since they know it’s critical to their health.  Repeatedly, surveys show above price and product, people leave because of dissatisfaction with the way they are treated.

But the level of dissatisfaction is qualitative and differs by customer.  One customer who experiences a single network issue may become enraged, while another may be more tolerant.   Knowing this and the value of each customer helps the company treat each situation with a custom tailored response.

That all sounds like common sense and easy, right?  Try doing it on millions of customers, with billions of bytes of unstructured data in their direct conversations and behaviors, and their indirect musings on social media, in blogs, and elsewhere.   Moreover, try to learn when each customer reaches various stages of interest or displeasure, and overtime improve your ability to predict these and take timely action.

Since the dawn of time, we learned that to survive we needed help from machines.   Use this newest breed of machines along with time tested investigation techniques to crack the enigma of your customers, gauge their state of mind, and delight them with personalized experiences.

Note:  These views are my own, and not that of my employer

Customer Data & Decisions – “Big Data – Big Value”

In my previous blog (“Big Data – Big Waste?”), I advocated about the importance of an upfront blueprint to help focus big data efforts in areas that lead to valuable insights.  Taking actions on these insights is ultimately how you glean value from your big data.

bigdata_value1

The 5th “V”

Strangely, many who espouse the virtues of big data rarely start by describing the value that can come from it, but instead pontificate about its attributes – Volume, Velocity, Variety, and sometimes a 4th V – Veracity.   Let’s talk about the 5th “V” – Value.

bigdata_value2

What is “Value” really?

Lasting value is created when there is a positive exchange between you and your customer. Yet if you sell something that doesn’t meet their needs, you create the illusion of value, only to see it wiped out later.   Conversely, discovering and acting on activity patterns can lead to explicit and latent needs being met, resulting in customer satisfaction and lasting value.  Tracking big data effectively can lead to these discoveries.

To illustrate, if I observe a customer’s repetitious buying patterns, and then offer to sell products in bundles, bulk ship them for less, or proactively send them, value is created for them – and you ensure a future purchase stream.

Let’s look at some examples of what firms are doing to unearth insights, take actions, and create value.

Real life examples

A leading automotive firm installs numerous sensors in high end vehicles that gather driver data –   predictive analytics warn drivers when fatigue might be setting in.   Farmers use wearables on cows, improving fertility and birthing success rates.

A major online retailer uses purchase history to predict what products you are likely to buy in the future, and stages those closer to reduce shipping time.  A travel site can monitor real-time flight activity, anticipate delays, and notify travelers – often before the airline does.

bigdata_value2b

These are but a few examples of the way firms are already using sensors, streaming big data, finding actionable insights, and creating value for their customers and them.

What should I do?

Ask yourself two simple questions:

  1. Is my company using modern data collection, streaming big data in real-time and using predictive intelligence to understand the patterns?
  2. Are we taking immediate action on these insights to enhance the customer experience?

If you answered yes to the first, but not to the second, you have the infrastructure, but without action will get no benefits.  If neither is true, you are falling behind by the day.  But it’s not too late.  Act now for value.

You’ll need a unified system that can ingest structured and streaming unstructured data, perform real-time analytics that monitor for patterns, decision strategies that arbitrate and trigger the right actions when unusual opportunity or risk is detected – and a system that can also automatically kick off processes to alert personnel, open a case, or notify customers.   Make sure to find a system that can give you this in one platform or otherwise you will waste valuable time implementing, integrating, and adjusting various pieces when you could have been creating value.

Comments and alternative views are always welcomed.

Note:  These views are my own, and not that of my employer

Customer Data & Decisions – “Big Data – Big Waste?”

Part 1 was about what firms really do know about me as a customer. Part 2 covers the ever popular topic of Big Data and why it needs a sponsor, action plan, and a solid analytic platform.

What did you say?

Did I get your attention with my somewhat controversial headline? Maybe it’s actually not that contentious because simply wiring to and capturing lots of data (e.g., Big Data) does nothing for you except add cost if you don’t effectively glean insight from it, and take action on it.   It’s no different than any other asset, in that if it’s idle, it’s sucking energy and not providing any return.   Like a big data black hole, where data enters but no insight can escape. How do you combat that?

blackhole

Have an action plan based on the kinds of customer decisions you want to improve, investigate data required, and constantly test, monitor, and refine that plan.   This plan will dictate what data you should be seeking and exactly how you will leverage it. In other words, work backward from your desired outcomes.

You might also be asking, what is big data? Good question.   As a participant in the business intelligence revolution, I’ve seen massive databases used for years for decision purposes. So what is new and different?   Actually, there are a few things.

First, customer data has been historically captured, scrubbed, matched and restored into on premise structured databases.   This led to the enterprise data warehouse with the so called “360 degree view” of the customer.   These systems required data expert intervention to add new data elements, were usually on premise, and latency rendered the view stale for today’s standards. Consumer and market expectations have evolved to expect on-demand and streaming data reflecting the latest and greatest view of the customer.

Second, since it ultimately required a target structured store, unstructured data, which is massive, became difficult to assimilate into one structured data warehouse.

And third, the variety of structured and unstructured data sources have grown, so much that again using an approach of trying to codify and blend all of that data into one mart did not meet flexibility, agility, and timing requirements of business people trying to make better decisions.

Ok, I need a plan. What next?

What if you could identify and sway vocal and influential customers? What if you could proactively identify customers at risk, and take actions to not only save the relationship, but turn them into ardent supporters?

Take these types of questions, and work backwards to formulate your plan.   Call it your big data blueprint.

worldascpu

Do you already know who the most influential customers are?   If not, start there.   How would you define this?   Conventional wisdom may first suggest it’s those with the biggest network of followers or highest NPS score. But upon further review, what might be more important is customers that actually frequently refer versus ones who say they will.   Working back, you would need data like mentions and referral codes. So determine the particular outcome, and then concentrate on connecting to the data you need to monitor and track those actions – viral actions such as re-tweets, re-posts, forwarded links, reference events, and such.   Then, rate your customers on that basis – building a Clout Score – the higher the score, the more clout they have with others and the more they refer you.   This score is then connected with actual behavior instead of formulations, surveys, or postulates.

Likewise, figuring out which customers are at risk, you might hypothesize that a major service interruption would put them at severe risk, and thus simply being able to run a query to find all customers impacted by key service disruption events would suffice.   Yet often, customer retention risk is much more complicated than that, and it’s likely that in this case you need a behavioral model that considers various risk factors, such as service disruption patterns, social sentiment, clout, customer loyalty, competitive options, and switching costs – and then test that model against real churn outcomes to calibrate its effectiveness.

Having sponsors is vital because invariably some aspects of your big data plan will involve capturing and leveraging data not readily available, and thus sustaining funding and resources to see your project through will require champions – people who believe strongly in the cause, and can help.

What technologies can help me get to my happy place?

We don’t live in a simple world.   We accept that, or get lost, frustrated, and fall behind – but we do expect technology will continue to help us navigate the intricate world.   So we seek the simplest and fastest solutions to complex problems.

Your answer is you will need many technologies. Accept that and do business on that basis. Select your stack based on requirements that your vendors are open, constantly invest in innovating their underlying technology, have exceptional integration both with their own sister products and with the outside world. Consider firms with a robust ecosystem and strong reputation for training, partners, and professional services.

Big data systems involve storage and retrieval of unstructured information, which is data that has not been highly codified from its raw form.   For example, data entered into free form text such as comments to blog posts or data collected from digital activity such as granular website click activity.   Big data is also real-time streaming data coming from various sensors that are always on, and stream data (often 24×7) such as devices that report precise location of objects (e.g., mobile phones).

Partner with a vendor that has solid, modern, and open technology, and has it in one platform. Beware of companies that get the marketing right and have compelling messages, slides, and even case studies, but under the covers have 2 or more actual platforms stitched together, and requires more custom coding to meet your requirements. How ironic that I’m warning marketers to be wary of the marketing!

Comments and alternative views are always welcomed.

Note:  These views are my own, and not that of my employer

Customer Data & Decisions – “Reflections of Me”

In this post, I explore what firms really do know about me as a customer.

reflection2

What do they know, and how did they get that?

Wow! Where do I start?   Many companies today are doing everything in their power to amass as much data on me as possible so presumably they “know me” and make more relevant marketing offers…or as they say, “to provide me with an exceptional experience through an ongoing conversation.”

As empowered consumers, we are the judge of whether they are doing this well. Are they really capturing the right information and in a way that is respectful, well-timed, and used appropriately? This subject quickly stretches into ethical and political implications, but to avoid that, I will just lay out some facts about what companies are doing:

  • First and foremost, they save everything I do with them. All interactions, all transactions, all orders, all clicks on their website – basically any activity on their physical and digital properties they capture and keep – in some cases for 4 years or more.
  • They can often freely share this information with subsidiaries and affiliates (which means a lot of other companies) unless I explicitly ask them not to.
  • They append 3rd party data – lots of it. The sharing of data about me is ubiquitous. Appending means other companies are capturing data and sell it and it’s often indicative of my affinity to like, want or to buy something. This can pretty easily be matched to me with a presumption, for example, I also like to golf because I subscribe to a golf magazine.
  • They are looking at my patterns of activity.
  • They progressively profile through very short but repeated data collecting. For instance, I sign up on a website and provide basic information, then I agree to a news letter, and they capture some preferences, I download their mobile app, and so forth. Eventually, they may know whether I own or rent, have children, or are planning a kitchen remodeling.
  • And they try to predict their next best move. In other words, they are trying to figure out what I really need and want. Called “Next Best Action” technology, and usually found in larger companies, there are very large teams tasked with calculating lifetime value, building rules, testing propensity models – and ultimately a hub that makes promotional, product and service recommendations.

Really very little of this is new my friends, it’s just massively accelerating.   In 1992, one of my favorite non-fiction authors, Erik Larson, wrote a book called “The Naked Consumer: How Our Private Lives Become Public Commodities.”[i] Back then, his impetus for writing the book was based on a pretty simple event driven mailing he received for his child’s first birthday. Intrigued, he chronicled a world he saw as already borderline out of control with consumer data sharing. Imagine his sentiments now with the growth of the internet, digital channels, social, mobile, and big data.   I think he might change the title to “The MRI of the Consumer.”  This month, Scott Brinker posted a blog entry estimating that nearly $22 billion USD of venture capital funding has been poured into the marketing technology companies he pastes onto his marketing technology landscape and admits it’s probably underestimated.

As a long time marketer, I’m not that paranoid or really that appalled at what is going on. I still believe we live in a world that has checks, balances, methods and free choices.   Often, as consumers, we decide how much information to give up in return for something.  In most cases it’s a conscious choice. And there are ways to combat and prevent abuse. My biggest concern is security, as information is repeatedly hacked and then used for purposes it was never intended for. Better security and education are needed, but in general I don’t think it’s as surprising today to the average person as it was for Larson 20 years ago.

But rest assured, this picture of you is getting clearer – and there is a substantial amount of corporate energy being poured into filling in the blanks. The popular term is “The customer journey”, and now also being called “The customer movie”, with the intent to define every frame.

Yet motives and reality are two very different things.   I might want to be rich, but simply wanting doesn’t make it so.   And really, who I am versus what specific habits or preferences I have in relation to a certain product or service is generally where the line is drawn. For instance, a home improvement business would love to know what kinds of building skills I have, what tools I have, and what projects I’m considering, yet I don’t think they really care about what music I like.

What do they intend to do with my information?

I believe at the heart, companies just want to sell more of what they have and do it at the lowest possible cost to them.   It’s that simple.   But they know the world is competitive, there are choices, switching barriers have eroded, and if what they are offering (or failing to) isn’t a match, or at the right price – I will go somewhere else.

So they collect data, study events and patterns of activity, test timing, try to get preferences right, personalize content, and hope I’m impressed when they take actions.event_detection

Are they becoming specialists majoring in knowing one aspect of me, and knowing it well?   Perhaps, but make no mistake their not your best interests are in mind, and if information is useful to another party, and a business transaction makes sense, it will happen. Ironically, businesses are better at sharing customer information then the healthcare industry is at sharing patient information, although finally we are seeing some improvement there.

How did they do that?

It’s really not rocket science, yet amusingly marketers are applying technology that is also used to help launch and guide rockets.

Space_Shuttle

When a rocket launches, there are sensors monitoring all its complex systems. As a consumer, your systems – what you say, what you do, where you go – are being monitored.   Hotels are now placing beacons at key locations such as the front door, to detect when you arrive.   Stores are using similar technology to gauge your potential interest in a product sitting on the shelf you are next to.

There is already software and technology, and the cost is dropping, to gather this data and allow the marketers to access it and build rules on it (e.g., if customer arrives, alert front-desk personnel and pop-up appropriate offers).

Rocket scientists make heavy use of statistics and probability theory to understand the amount of redundancy necessary in systems, the likelihood of something failing, or predictions of weather to gauge best launch and landing windows. Marketers use all these techniques to tune their systems for response time versus cost, whether a new promotion will succeed, or timing a communication.

Also, the cost of storing, aggregating, distilling, modeling, and using this information is dropping rapidly.   The internal discussion has shifted from how much data should be saved, to how more data can be synthesized and insights gleaned from it.

A confluence of freely shared institutionalized best practices, application speed and simplicity, cloud computing, automation, and scientific testing procedures has led to more companies with access to better marketing technology – and a better, albeit still incomplete picture of you the customer.

Comments and alternative views are always welcomed.

Note:  These views are my own, and not that of my employer

[i] Larson, Erik. The Naked Consumer: How Our Private Lives Become Public Commodities. New York: Penguin Books, 1992.