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.”

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

 

My 2019 Martech articles

To CDP or NOT – 3 tips – then you decide

4 Golden Rules for Knowing and Honoring Thy Customer

Dear CMO: Sorry, but we need a CVO (Customer Value Officer)

A 6 pack of tips when replacing creaky MRM software

The Final 4: MarTech Platforms and Ecosystems

Will AI in digital marketing lead to marketer obsolescence?

One-to-One Marketing: 20 years later, are we there yet?

Marketing’s Strangelove: How I Learned to Stop Worrying & Love Service

5 predictions for CRM’s AI applications in 2019

Consumers kill for digital convenience: Can AI help your business?

We’ve all seen countless images of the proverbial empowered consumer.  That mythical creature seeking convenience and instant gratification.  It’s a conjured-up image of a time-strapped digital native that juggles five devices and 15 tasks, interacting simultaneously on a host of channels, using their super-human consumerism to wield terrifying powers capable of paralyzing unworthy brands.

AI in business

Hyped-up as they are, these visuals still serve a healthy purpose.  They remind us just how far digital bars have been raised, and that should cause pause and beg the question, “as businesses, are we measuring up?”

Collectively, the answer is we’re not.  In fact, consumer satisfaction studies repeatedly confirm it.  Simply search on, “consumer study poor digital experience” and voila – hundreds of examples.  One study conducted by Software Advice found over 90 percent of consumers had one or more deal-breaker digital experiences when seeking customer support on mobile[i].  So, in an age with so much technology at our fingertips, why are we falling short?  What can we do to fix this?

Too often, we fall short because we focus on the wrong problems in the wrong order.  To correct this, it’s important to first consider a modern consumer’s mindset and what they’re demanding.  With greater resolve, they’re chasing after nirvana, in a quest for brands that deliver products, services and experiences that are:

  • Valuable / relevant
  • Consistent / high-quality
  • Enjoyable / attractive / personalized
  • Familiar / trusted
  • Secure / lower risk
  • Compatible with values / social beliefs
  • Convenient / simple / timely

Enterprises, however, can’t perfect all seven of these deadly-important areas simultaneously.  So, the trick is finding what matters most, and then using AI and automation technologies to help.

AI in business won’t magically transform a company with fundamental structural flaws, such as poorly designed products, no unique selling proposition, or cost containment issues. These take great human leadership, creativity, and collaboration to fix.  And it won’t manage the job of building and maintaining corporate culture.  But in other cases, AI applied pragmatically to streamline processes and eradicate friction can make an enormous difference.

What’s proven to be a winning recipe in business is paying attention to customer-centric details.  Brands hyper-focused on customer experience build a lasting reputation and increase in value.  Look at Apple, Uber, Airbnb, Amazon, and even Booking.com.  All built on the backs of nailing digital experience, often with a mobile-first mentality.  Yet, with seven major areas and hundreds of experience details to consider, where should you start?

Is convenience king?

Out of the above seven criteria, convenience may be the most important in terms of driving long-term value, and the one CX professionals can influence the most.  Perfecting convenience can separate winners from losers; sellers from re-stockers. Consider this quote from a CEB study[ii]:

“Brands that help consumers simplify the purchase journey have customers who are 86 percent more likely to purchase their products and 115 percent more likely to recommend their brand to others.”

AI in business

And convenience contributes to and builds up other factors, such as being viewed as valuable, familiar, and trusted.  It may be one of the chief drivers of loyalty.  It can even trump something like price.  For example, wireless carriers have learned consumers prefer unlimited communication plans because they’re convenient and simple, even though they may cost more[iii].  Consumers make impulsive and emotional purchase decisions when enough of the factors align, and tend to justify things afterwards.  Since consumers’ assessment of convenience is qualitative, figuring out how to elicit positive emotional responses regarding convenience is crucial.

In a consumer’s mind, the label of convenience translates into a business being viewed as:

  • Useful and suitable
  • Easy to buy from, use, and transact with
  • Requiring less overall effort
  • Simple to understand / responsive to issues
  • A time saver

Each is a judgment call by an individual, but with critical mass and time, these opinions converge to a collective market consensus (the wisdom of the crowd).  They manifest themselves in the form of review scores, ratings, and tribally-shared social advice.  It’s this reputation that drives commercial allegiance.

Largely, consumers make emotional decisions when they choose one product over another.  Sometimes they want combinations that are seemingly impossible to get:

  • A readymade desert that tastes great and is nutritional
  • A car that is inexpensive, fast, great looking, economical, and durable
  • A delicious pizza that comes in a few minutes, is made by an environmentally-conscience brand, and oh…costs less than $10

It’s no wonder brands struggle to satisfy whimsical consumer desires, but fickleness aside, they cry out for brands to simply simplify things.  Ironically, they work longer and harder to live in a world that supplies them with exploding choices for everything but precocious little time to weigh options, which in turn drives them to crave simplicity in decision making. They demand trusted information that is easily accessible.  They want user-friendly ways to weigh options, and help navigating processes.  In a 2016 survey on travel shopping preferences, consumers picked ease of use as the top reason they booked using an online travel site.[iv]

AI knows there’s no second chance to make a first impression

Consumers want convenience, but which actions will achieve maximal impact?   Before answering this, keep in mind a marketing 101 maxim: perception is nine tenths reality.  And perception is often built-up on first impressions.  Further, when an initial impression goes wrong, it takes multiple positive interactions to repair it.  As such, consider using AI as tooling in helping elevate levels of perceived (and real) overall convenience in critical first-impression customer journeys such as:

  • Getting a quote
  • Completing an application
  • Navigating a sign-up or onboarding process
  • Completing an initial purchase
  • Setting up online payments

And during service scenarios such as:

  • Order status checking
  • Returns
  • Claims
  • Lost card replacement process
  • Scheduling an appointment
  • Finding a doctor

How does AI support these?  If we agree that AI is a mixture of automation and intelligence technologies, AI can help streamline the process for consumers getting answers such as the status of an order, return, or claim.  Further, consumers can even ask these systems to schedule a store or branch appointment, find the most convenient time and location, and then add the appointment to their calendar.

AI-powered chat bots (and other self-service portals) can provide 24 x 7 first-line support for answers to questions like:

  • How to transfer funds
  • Make an online payment,
  • Get account and policy status

In many cases, without any human intervention, bots can answer questions, close out an inquiry, and even assist with completing a transaction.  In situations requiring human agents, AI-based systems can orchestrate seamless hand-offs of data and case details, allowing humans to pick up precisely where machines left off.

Make no mistake, AI skills are already going far beyond performing simple tasks.  Today, AI engines can give nuanced advice, surface unique insights, and provide proactive recommendations.  The most sophisticated systems even factor in customer context, such as location, weather, mood, and motivation before arbitrating on the next-best-action.

In banking, for instance, AI can help track savings and spending habits, and send threshold alerts. To illustrate, suppose a consumer has a recurring transfer from checking to savings each month.  AI can monitor account balances and send an alert when upcoming bill payments are forecasted to drain a checking account beyond non-fee thresholds.

In healthcare, there’s Dr. AI from HealthTap, who can engage in conversation aimed at providing triage and care advice, using a locally-stored health profile, a network of over 100,000 doctors, and Bayesian learning AI to serve up the next-best-advice.

What’s the right set of technologies for your stack?

Well, there’s good news and bad news.  First the bad news – there is no one right answer, and with thousands of vendors (6,829 in this marketing landscape), open-source packages, and resulting combinations of solution stacks possible, there’s no evidence anyone has found the absolute best combination, or ever will.

Now the good news – you have a ton of alternatives, with many combinations likely to work, but finding a stable and winning blend is tricky.  Some tools, on the surface, look easy to use but aren’t.  Others won’t live up (functionally) to their marketing hype.  The best advice is to form a solid basis with at most one or two platforms covering essential infrastructure (that you can’t afford to switch in-out), and make sure these platforms allow for plug and play with adjacent pieces likely to have shorter useful lives.

For example, find vendors with durable connectors for wrangling data into an actionable customer profile, a real-time hub that acts as a central brain to arbitrate customer decisions, and integrated customer analytics.  These components are foundational, and must be centralized so they operate in a channel agnostic fashion.  New channels may spring up, and others diminish in importance, but a decision engine which feeds on key behavior data, arbitrates decisions, and renders appropriate next-best-actions is a necessary constant.

Final thoughts

There’s a real irony forming with AI in business.  We’re building and teaching computers to be more human, while as humans we’re being led and conditioned by our busy lives and workplaces to be more machine-like.  The problem is computers are no humans, and humans are poor computers.

Step back and consider what’s best for the consumer.  Providing great first impressions, as well as seamless and gratifying ongoing experiences, requires well-functioning and well-behaving humans and machines working in concert.  Consumers want products and services they’re proud to recommend because they make life easier and more enjoyable. When things go wrong, they expect flexible help and fast solutions.  When self-service isn’t working, they demand cases smoothly transition to well-informed, caring, and compassionate humans.  Brands must skillfully, judiciously, and mindfully weave together computer systems with humans as they design for convenience in all the complexities of customer journeys.

Delivering convenience must be a paramount goal, so reflect on the unique characteristics of the individuals you serve and the nuances of their voyages.  Dry run how each will navigate your services:  some will be older and less familiar with technology; some will be capable of juggling five devices on five channels; sometimes technology will fail and require fallback processes.

Ultimately, your convenience reputation will be defined by a diverse set of consumers steering through a wide variety of conditions and processes.  Use AI and humans to start off on the right foot, deliver consistently under normal operating conditions, and to proficiently handle the inevitable miscues.

[i] https://www.softwareadvice.com/resources/improve-cx-with-mobile-support/

[ii] https://news.cebglobal.com/press-releases?item=128138

[iii] https://www.theverge.com/2017/2/17/14647870/us-carrier-unlimited-plans-competition-tmobile-verizon-att-sprint

[iv] http://www.traveltripper.com/blog/why-do-travelers-prefer-booking-with-otas/

 

8 AI trends for Martech

In this 8th and final short video in my Machine Marketing Series, I give my views on the “The HOTTEST AI trends for Martech” to keep your eyes on in 2018.

 

I cover eight key AI trends to keep a watch on:

  • AI data and processing speed
  • Natural language processing (NLP)
  • Image recognition
  • Natural language generation (NLG)
  • Automation and process management
  • Transparent / Explainable AI
  • One AI brain
  • AI organizational dynamics 

8 MACHINE LEARNING for marketing areas to watch in 2018

If you’re like the unbreakable Kimmy Schmidt and got stuck in a bomb shelter in 2017, it may be both a blessing and a curse that you missed the machine learning for marketing media frenzy.  Machine learning showed up everywhere, rivaling electricity’s systemic emergence a century ago, allegedly injecting sage-like wisdom into everything from sales forecasting tools to email subject lines generators.

machine learning for marketing trends

But buildup and hype aside, real progress was made in using machine learning for marketing purposes, infiltrating impactful areas as unprecedented investments poured in.  More resources supporting great minds pushed forward innovation in areas like image recognition, voice technologies, and natural language generation (NLG).  And savvy brands that mindfully wired these into marketing applications boosted performance, in some cases realizing 400 percent ROI.  Here are eight areas worth watching in 2018 that saw significant advancement and are well-poised to advance further.

 

Big data and a need for speed

Like real estate’s mantra of location, location, location…. machine learning’s very foundation and success are predicated on its thirst for big data and its need for scaled-out, lighting-fast processing speed.

But for data lovers, just as the internet giveth, during its unabashed wild-west data rush era, privacy laws spurred on by libertarian outcries soon may taketh it back.  So, keep an eye on data privacy regulations, such as GDPR (which takes effect in the European Union in May 2018), as they could seriously impact future data availability.

Regulatory environments notwithstanding, with abundant data stockpiles and processing speeds continuing an inexorable march forward (vis-a-vis faster GPUs and cloud computing), expect more advances.  For example, firms will latch onto progressive profiling and incremental data hygiene methods to refine first-party data, as emphasis shifts away from second and third-party data sources subject to stricter privacy regulations.

Capital One did just this in a routine email sent in late 2017, when they requested members update annual income data on file (previously obtained by appending from a third-party source), suggesting that if customers cooperated, higher lines of credit would be their reward.

2018 will see more of this.  Organizations will harvest their big data crops, sifting off customer behavior insights aimed at deepening relationships and selling more products faster using less resources.  Anticipate more investment in customer data platform, compiling, virtualization, and rationalization initiatives, with more computing horsepower and human capital helping the harvesting efforts in 2018.

 

Marketers!  You need bionic ears & AI voices

As humans, we’re obsessed with creating and perfecting tools that overcome our limitations, take our skills to new levels, and make our lives better.   And last year marked the point that AI devices such as natural language processing, text analytics, and language generators stormed the commercial scene and provided marketers with enhanced listening and speaking abilities.

Listening means understanding not just hearing.   Enterprise marketing experts were graced with technology that can listen and understand millions of customer inputs simultaneously across a plethora of channels.   Call scripts, reviews, complaints, social posts, and a host of other forms of feedback can be ingested, concept labeled, checked for sentiment, and gleaned for intent.  Look for more applications and advances that propel the viability of using tech to listen and understand the voice of the customer at scale.

CRM AI - Voice recognition

Source: http://www.scmp.com/news/hong-kong/economy/article/2080503/hsbc-launch-voice-recognition-hong-kong-phone-banking

Although Siri, Alexa, Amelia, Cortana, and other AI assistants weren’t born in 2017, they arguably came of age, infiltrating our homes, and entering the workplace.  If you didn’t catch it, Amazon announced Alexa for business at its re:Invent conference in November.  Machine voices will continue to spread to business places like conference rooms, service channels, products, and kiosks.  And companies (such as HSBC, Citi, and Barclays) found voice signatures another reliable biometric authentication tool to streamline digital transactions.

In 2018 machine learning may not replace you, but using it to handle routine tasks, listen to and converse with customers, and accept it as part of your marketing, service, and sales team will be essential to your survival, as you’re asked to up your productivity and customer experience enhancing game.

 

Put machine learning’s eyes on customer data, journeys, and marketing content

Discovering, understanding, and learning from customer journeys requires mechanisms to observe and quickly answer question such as:

  • Which customers are eligible for offers, got them, and responded
  • Where do customers struggle, pause, or get stuck in their journeys
  • What sequence of offers and channels lead to conversion (attribution)
  • When do certain customers show up on the marketing radar; and when do some drop off and why

Marketing specialists started using journey analytics to piece together the customer behavior puzzle, and the tech got better at going beyond business intelligence guesswork to prescriptive AI.  More AI vendors bubbled up offering solutions that don’t just sum and sort data, but provide an analysis layer peppered with NLG narratives (such as Narrative Sciences and Arria).  Others majored on providing better path-to-purchase journey visualizations, like Clickfox and Pointillist (although its arguable whether these are really AI tools).

And some focused efforts at bringing image recognition to real machine learning for marketing use. Deep learning and image recognition applications went far beyond surfacing that labradoodles and fried chicken appear related.   AI image processing proved its mettle for filtering and categorizing marketing and sales content, helping marketers better understand customers’ content needs and serve them appropriate and relevant content and offers.  Brands began expediting and personalizing services using the ubiquitous smartphone and AI’s ability to pinpoint products and people in pictures and video.  For instance, Aurasma launched an app that democratizes adding augmented reality to a consumer experience by simply triggering a video or animation overlaid on a smartphone screen based on recognizing a pre-defined image.

 

“Hey AI!  Create me some emotionally compelling content”

Marketing pros earn their pay by crafting compelling content using words and visuals to express value and elicit responses.  They dance their evocative content lures in front of consumers knowing those customers will strike if needs are met and emotions satisfied.  But up until just recently, most of these assets were home spun.

Yet last year, avant-garde marketers began applying AI to content generation, realizing that to compete in the new world (where content must be both mass produced and highly personalized), old tools must give way to new ones.

CRM AI - Natural language generation (NLG)

Source: https://blog.7mileadvisors.com/natural-language-generation-the-game-changer-for-the-21st-century-16b5a7ed3336

And firms like Persado began facilitating the march toward marketing’s creative nirvana, using NLG, emotional science, and machine learning to optimize (down to the preferences of an individual) the attractiveness of marketing offers by altering language, font, color, position, and other creative formatting.  Results are not just encouraging, they’re somewhat staggering:  click-through-rates (CTR) increased by 195 percent; conversion increased by 147 percent.

In one case using this technology, Amex Rewards generated 393,000 versions of engineered copy for its banner ads aimed at getting a customer to burn down their rewards points.  The winner drove an 8.6% conversion rate, thumping the control’s 3.5% rate.

 

Self-driving marketing – Your AI digital agency

Practitioners continue to debate whether machine learning data prep, analytics, and marketing in general can be fully automated (particularly at the enterprise level), but nonetheless, the tools keep coming.

To this end, an interesting arrival on the scene was a vendor called Frank.ai, albeit clearly for down-market marketers.  It’s literally 8 steps to setup and run a multi-channel campaign:

  1. Enter name and dates for campaign
  2. Select audience by city, interests (mix of music, pop culture, shopping, sports, etc..) or look-a-like targeting; age (typical bands); gender; language
  3. Decide on display ad on desktop or mobile or both
  4. Specify budget (e.g., $1000)
  5. Upload display ad creative image
  6. Add social media promotional ad (if desired)
  7. Add URL for click through (analytics tracking automatically setup in Google Analytics)
  8. Enter payment method (credit card or PayPal)

Simple and unsophisticated?  Check.  Will this kind of tech put further pressure on enterprise vendors to make their tools easier to use?  Check.

 

Explainable machine learning for marketing

As machines crunch data, score customers, make predictions, and automate marketing, being able to explain to humans what’s going on and why is becoming more important.

Some models are very opaque, and simply can’t explain themselves.  Given this, firms will need AI controls in place (such as offered by Pega) to prevent opaque models from being deployed in certain situations. Others are more transparent, easier to tease apart, and safer to unleash.  Research and applications are stepping up in this area, so stay tuned, especially as more regulations emerge such as GDPR, that dictate data rights and demand algorithmic transparency.

 

Building one machine learning for marketing brain

Like opinions, everyone seemed to have an machine learning software brain to peddle in 2017 including:

  • Watson from IBM
  • Einstein from SFDC
  • Sensei from Adobe
  • DaVinci from SAP
  • Magellan from OpenText
  • Always-on Customer Brain from Pega

What was less clear, however, was if each had one coherent well-integrated brain – or instead a multitude of disparate intelligence modules from the various acquisitions.  In the case of SFDC, for example, between 2012 and 2016 they acquired 21 companies, of which at least nine had some form of machine learning for marketing tech.

Stay tuned to AI developments from these and other leading marketing technology vendors, and pay close attention to whether they demonstrate real intelligence integration in the solutions they sell.

 

Machine learning for marketing organizational dynamics

Accomplished scientists and artists have rarely been cut from the same cloth.  In 2017, Walter Isaacson released his long-awaited masterpiece, the biography of Leonardo da Vinci, adding it to his corpus of history’s best examples of exceptions to this rule (Ben Franklin and Albert Einstein being other similar biographies he’s written).

So rather than wait for enough Leonardo types to come along, organizations would be wise to work toward making connections across machine learning and creative disciplines, which will be key to maximizing their capacity to innovate.

Along with attracting, merging, and retaining the right talent, brands must also acquire the right machine learning technology, but even more important is having a concerted AI strategy closely coupled with business objectives and marketing improvement goals.   It’s imperative to work from well-defined use cases and clearly articulated outcome definitions backward to the technological and data solutions necessary to support them.   Further, firms must use nimble organizational structures with small teams made up of artists and scientists; IT and the business; re-aligning resources into small digital factory teams that are wed to agile methodologies and collaborative approaches.

2018 and beyond

In all, 2017 was a banner year for machine learning for marketing, in terms of both hype and legitimate commercial progress.  Keep track of these eight areas, and you’ll be following the most interesting and promising leading-edge AI technologies and trends that will prove paramount to success in improving and automating marketing and customer experience.

AI-Based Promotions – Welcome to the Creative Machine

Mad Men & AI - Promotions

Source: Exploration of Saturn’s Moon’s by Kacper H. Kiec

As a Marketer, when you craft successful promotions, you’re especially proud of their creative aspects.  And it’s understandable because creativity seems our last bastion against the perceived onslaught of machine domination, so we fiercely defend that turf.  The tenuous argument being, “robots are no match for human creativity!”  This viewpoint, besides inviting a cage match between humans and machines, also smacks of keeping math and machines out of any solution, lest boring and stiff digital influences ruin the warmth of our marketing art and experience show.   However, for all the aspiring “Michelangelos” out there, it’s time to rethink this, lest you find yourself selling one-off ad creatives at street-side craft shows.

A promotion is fundamentally your story; your pitch in a nutshell – delivered through a channel to an audience of one – assuming it gets through.  And the fact that it oozes creativity and garners the right emotional response can be critically important to a customer’s reaction.  But what is its true worth? Compared to what?  Is there a chance that for most eyes it will succumb to fading into the backdrop with all the other one-size for all advertising clutter?

With a fickle, time-pressed consumer, your promotion has – at best – a fleeting chance to capture an individual’s attention, make an emotional connection, explain a deal, plus convince that person they should care.  On average, you’ll get about five seconds to grab interest; succeed and you may earn another five to emotionally connect, and so on.   In most cases, no matter the channel, you’ll be afforded about thirty seconds, a few minutes tops – to deliver the goods.

Given this, every top-line pitch needs a “No Boring Zone” mentality with visually appealing facets – nonetheless cookie cutter theatrics alone won’t win the day.  You need to get serious about how to use math along with machines (artificial intelligence) to radically fine-tune sales messages and custom-fit them for individuals – in other words, personalize them.  To do that requires scaling up a promotion production and testing factory.

A canvasing of the available marketing automation tooling finds that very few help solve for the bona fide business problem of creating and testing a wide variety of promotions across a plethora of channels.  In fact, most simply give you a facility to manually key enter the metadata for each version, creating them from scratch – calling this Offer Management or an Offer Library.  The problem is as an artisan, you basically run out of material and time in a futile attempt to manufacture a decent collection for the library.  Thus, the conundrum –  to cut through the noise, and find the right version that resonates for each nuanced individual, you must create and test thousands of versions, but old-fashioned human means alone cannot keep up.  And if you muster the means to produce numerous alternatives, it’s equally difficult to monitor their effectiveness and pick the winners.  You need tools that automate mass testing and response tracking, and math to tell you exactly what’s working and why, yet few such tools exist.

Everyone talks about knowing customers better; using that knowledge to personalize.  It’s an admirable aspiration.  However, commendable goals don’t necessarily translate to better outcomes. In this case, it doesn’t matter how well you know customers if you can’t hyper-customize content, messages, and other creatives – and produce tailor-made promotions that really fit what customers expect in the moment of interaction.

You won’t entice my response by extrapolating from a few of my preferences and placing me into some huge segment.   All the “Hey, Vince wouldn’t you love to travel, drink exceptional wine, and eat at these fine places” in the world won’t matter if I don’t get something that is fabulously timed, speaks directly to me and visually jumps out, elicits an emotional connection, stays engaging, and commands attention due to its specific relevance – in other words the message needs to be personalized to my promotional preferences and exact product needs.  In fact, the promotion itself (in its entirety) must be an enjoyable experience.

Moreover, the same goes for financial services, transportation, telecommunications, insurance, and healthcare promotions.

Marketing’s 4th Dimension – Promotions

Marketing technologists (martech types), and the automation applications available to them, tend to focus mainly on these big three dimensions that drive response rates:

~Data:  Stockpiling and codifying key customer data

~Behavioral Analytics:  Gleaning intent and preference, scoring response propensity, and segmenting

~Channel & Time Optimization:  Delivering messages through the right medium at the right time

 

Space-time warp

All of these dimensions are important pieces to solving overall marketing optimization.  However, without the ability to generate thousands, if not millions of promotions (with varying copy options, incentive levels, calls to action, creative versions and such), about one third of what drives response and conversion is woefully underserved in assuring messages are noticed, relevant, and responded to.

Presently, this 4th dimension, promotions, has received practically no attention from marketing automation technology and AI – and instead marketers merely accept that snail-like non-scalable A/B testing is the best way.  The fact is, even with armies of humans crafting variations and A/B testing, the number of manageable versions you can juggle will be in the hundreds at best – when what you need to compete is the ability to create & test thousands of these.

Ok, not convinced yet?  Then perhaps a little math is in order (as he locks the classroom door and places nails…I mean chalk… on chalkboard):

Problem: Calculate the number of email message variations.

Email promotion components:

  • 100 products to sell
  • 10 images per product
  • 10 subject lines
  • 100 email templates (to test fonts, color, container locations, call-to-action button)

Answer:

100 x 10 x 10 x 100 = 1 million promotional variations

News Flash!  You have no chance with just brute human force to create and test this many variations.

 

Lucy & Ethel couldn’t keep up – and neither can you

chocolate factory

In this famous Chocolate scene from I Love Lucy, an illustrious TV series from the 1950’s, Lucy & Ethel prove that manual human labor, no matter how clever, can’t keep up – quickly becoming the bottleneck in an otherwise automated system.

Given this seventy year old lesson, why do we think that humans alone can drum up and test an acceptable level of promotional assortment?  They can’t.  But still, stubbornly, we hand-crank creative versions, accepting less variation.  Yet the better way is to let people fashion the promotional raw materials as re-usable creative elements, combined with letting artificial intelligence test the combinations – surfacing the winners – automating and individualizing the wrapping of your chocolates.

Marketers, as well as many businesspeople, are warming up to the current power and future potential of AI and what’s at its core – Data Science.  In fact, in a recent study by the Boston Consulting Group of more than 3000 executives, 61% of those surveyed see developing a strategy for AI as urgent[i].  And in this case, machines and math can assist.  As a marketer, you already know the power of AI and machine learning.  It’s what helps you calculate customer value, score a customer’s propensity to respond to a given incentive for an applicable product, and even predict when to present the offer.  And to get started, you don’t need a million options.  Instead, use human judgement to field a reasonable set of challenger creative components (perhaps a dozen of each), then use AI to perform champion –  challenger tests on the combinations.

Exactly how will AI and machine learning help generate and test copious quantities of creative offer variations?  Enter natural language generation and automated (multivariate) testing.

Natural Language Generation (NLG), Visuals, and Templates

In our email example, we discussed written variants (e.g., different subject lines), various visuals (fonts, graphics), and template alternatives (where to place the copy and graphics).  Let’s break these 3 elements down:

Natural Language Generation (NLG)

Computers can generate language.  In fact, they’ve been doing so for over 30 years.  Today, they can even take into consideration emotional aspects. In 2015, Gartner went on record forecasting that by 2018, twenty percent of all business content would be computer generated[ii].  Although aggressive at the time, and unlikely now, it still highlights the potential of NLG, and progress nonetheless has still been impressive.

For marketers, there’s already good examples of how NLG is used today, and can be helpful in solving for the promotional version dilemma.

For example, Persado Go uses NLG to generate variations of email subject lines, and then records performance broken down by specific elements such as emotions, formatting, descriptions, and so forth.  Candidate subject lines are generated from a huge database, and a sixteen-version test is setup.

Visuals

Visuals are combinations of text aspects (font type, styles, size), color, video, pictures, and graphics. A picture is not only worth a thousand words it’s also capable of sparking an emotional connection.  And although AI is encroaching on even this human endeavor, for now people (assisted by AI) are still superior to pure machine generated creative assets.

Templates

Templates drive how you both organize and showcase content.  For an email, it controls where recommended content will display, where a call-to-action button will be placed, what font will be used for written copy, and so on.

As with any element, a wide assortment of templates should be tested, each with innovative ideas about where containers should be located, and which font and color scheme will work best.

Now that you have all the ingredients, just mix and serve.  Except how will I know which versions work best in which circumstances?

Multivariate Testing & Adaptive Machine Learning

Enter multivariate testing – which sounds complex and geeky – but it’s not that difficult (although admittedly the term is geeky).  A multivariate test is simply a series of A/B tests, done simultaneously – which means you won’t spend months testing; instead doing one test (testing a string of modifications all at once) in as little as a few days or weeks.

And using an adaptive machine learning approach, such as this one available from Pegasystems (in full disclosure I do work for Pegasystems), the whole testing process can essentially run automatically, as the machine (the math algorithm) determines the eventual winners by ranking them higher as the digital response evidence pours in on which promotional variant get the best take-rate in which situations.

You and The Machine will go far

Too often we fall victim to pitting ourselves against machines, rather than exploring a symbiotic relationship with them – like the one we have with our smartphones.  As marketers, we need to think the same way.  AI can assist us, and we must embrace that.  Exploit technology for what it does well, and weave that into your promotional factory, leveraging its ability to scale things to new levels never imagined with manual methods.

[i] S. Ransbotham, D. Kiron, P. Gerbert, and M. Reeves, “Reshaping Business With Artificial Intelligence,” MIT Sloan Management Review and The Boston Consulting Group, September 2017.

[ii]Gartner,  http://www.gartner.com/smarterwithgartner/gartner-predicts-our-digital-future/, 2015

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.

 

Customer Engagement – From BI Guesswork to Prescriptive AI

Customer Engagement approaches, and the technology used to enable them, have evolved immensely over the last 25 years.  Two distinct eras define this period, as well as a major technological shift to real-time systems with AI feedback loops.

Prescriptive AI

The BI Guesswork Era

During the advent of the Business Intelligence (BI), Marketing Technology and Campaign Management era (circa 1990), marketers had limited predictive powers.  In many cases, when it came to what individuals really needed, they resorted to guesswork.  They channeled their energy to perfect efficiencies in targeting and automation.  Their main emphasis was finding an approximate audience for products so they designed promotions for large segments of the population. They fixated on finding segments that fit into certain “likelihood to respond” buckets, and then repeatedly tested timing, messages, and creative content by peppering those segments with treatments.  In other words, they identified massive groups, matched offers to these groups, and then used technology to systematize their marketing.

Although some of those marketers drew on basic models (such as RFM – Recency, Frequency, Monetary), which provided rough guidance on how deep to mail into a file, most didn’t even do this.  Typical response rates were 0.5% at best.  During this period, the average adult was receiving about 50 pounds of junk mail a year – coined junk mail because the promotions were irrelevant 99.5% of the time.  Thus, the majority viewed this activity as frivolous, mocking it with nicknames and jokes.  Regardless, marketers were unrelenting as they continually carpet-bombed until consumers either responded or learned how to opt-out.

Their tools of choice were crude in nature.  They were slow, not fine-grained, and certainly not customer-centric.  Usually, the campaign flowcharts they devised utilized basic analytics where deterministic queries ran against databases returning huge customer lists called segments.  If there was any further segment refinement, they relied on business intelligence technologies like OLAP (Online Analytical Processing) and dashboards to support their intuition.  Even as some of the more sophisticated marketers attempted predictions, providing those models with feedback was nearly impossible due to the batch processing nature of the flows and platforms they employed.  As shown in Figure 1, although some crept up the analytics value chain toward being predictive and answering the question “What will happen?” most fell short.

Figure 1:

business intelligence

Source: http://www.bi-bestpractices.com/view-articles/5642

Using a backward approach, engineers pre-developed the product, and marketers wrangled the packaging, promotions, and messaging to the audience – again using more guesswork than analytics.  It was difficult to react contextually, at scale, to actual individual needs, so instead they focused on groups of customers.

And so they executed bulk outbound communications at scale. With promotional ammunition in hand, readily available data afforded them reasonable targeting coordinates, and computers and devices served as the delivery mechanisms. The marketplace and emerging technology supported a numbers game and rewarded short-term economic gains.  Longer-term loyalty and longitudinal effects took a back seat.

By the turn of the century, direct marketers were plodding ahead using ever-richer consumer profiles that enabled them to focus promotions on increasingly smaller segments.  And even though in 1995, Peppers & Rogers had coined the term “1:1 marketing,” enterprise marketers were no where near direct conversations with individual consumers.  Still constrained by scale, they were stuck communicating to segments, albeit smaller and smaller ones.  What they didn’t realize was they were about to hit a wall (Figure 2)

Figure 2:

Real-Time Evolution

By 2005, marketers had the tools to perform hyper-targeting.  They aggressively tested different incentives, creative elements, and fine tuned things based on response metrics.   Scoring models were refined, though the expense was large, and the iterations long.  The results didn’t so much alter someone’s behavior, but more provided alternatives to consider, often ones that still had borderline relevance to a current need.

Often the goal, instead of steadfast loyalty, was simply to increase immediate purchases with minimal marketing waste.  In theory, if targets responded and steadily purchased, no matter the purchase, more purchases should follow.  Supposedly then, over the long haul, the business accomplished its goal of capturing more share of wallet.

Around 2010, some leading edge marketers who realized the value of a real-time approach, began hitting that wall.  The foundation of the system they had spent 15 years building was the wrong foundation.  It was a platform built for segmentation, and it supported the wrong approach. They needed a “Real-time 1:1” platform, customer-centric prescriptions, and a more dynamic feedback loop.

Enter the Prescriptive AI Era

Good marketers have always been similar to psychologists in that they study consumer behavior. With today’s data and technology, it’s possible to take engagements one-step further – diagnosing, and treating those customers to alter their behavior methodically over time.  Stealing a page from the broadcast advertisers’ playbook – who use “subliminal seduction” – many marketers are marching toward implementing systems that use incremental and proactive drip therapy to persuade inner minds toward brand myopia.

The only piece missing from the puzzle is a real-time platform.  Traces of this began appearing in 2010, as big data systems, parallel computing, solid-state storage, and other technology advances drove computing costs radically down, and speeds up.

Today the pieces are in place, and more are climbing aboard, as real-time platforms have fully emerged and are cheaper and more reliable.  It’s now feasible to use customer-centric prescriptive tactics at scale and get huge lift over baseline approaches.  Models can predict behavior to an amazing degree of accuracy.  The artificial intelligence (AI) models both diagnose and – using Decision Management – proactively prescribe next-best-action engagement treatments.

Figure 3:

next-best-action

Everyone knows engagement professionals today have more channels.  They’re no longer constrained to broadcast media delivery systems (that lack dynamic feedback loops), and can now use digital response media and even physical surveillance.  And with this plethora of channels, they can administer and perfect personalized, contiguous, and hypersonic stimuli-response strategies.  Essentially, they can employ an always-on brain, powered by rich consumer data, advanced machine learning algorithms, and a 24 x 7 continuous learning loop.

What’s more, these machine learning technologies and embedded predictive algorithms can work in a very deliberate and intelligent way, dynamically creating conditional content and promotions, each time consumers reengage on a digital channel.  Incremental repeated responses (or lack thereof) allow these models to learn, tune themselves, and in essence direct and alter the future – programming individual behavior.  Customers are enticed to reveal ever-increasing amounts of personal information, in exchange for points or some privilege, trusting the exchange is amenable, and the information use one-dimensional.

All of this behavioral activity – social, purchase, demographic, and so forth – is recorded, with the aim of feeding it back into those same algorithms that iterate to find new patterns, refine predictions, and subsequently inform Decision Strategies that recommend the next series of treatments.  In some cases, these systems can even run autonomously, using advanced data science techniques such as genetic algorithms, game theory, and reinforcement learning.  System designers seed the rules of the game, configure the objective function and constraints, and then push “Go.”  The designers and their business counterparts peer in on occasion to monitor whether goals, such as higher loyalty and profit, are trending in the right direction.

Figure 4:

AI Learning Loop

Although this suggests overt manipulation, it’s not necessarily malevolent.  Provided customers have choice (and are well informed and discriminate), and businesses operate ethically (on a level playing field), the economic scales can still balance, and brands that provide products and experiences with the best value can still prevail, and consumers get a fair exchange of value.  You may have noticed, however, a few important “ifs” in this last statement.

Whether we like it or not, we now live in the Prescriptive Era, where the mission of brands is to get to know us, maybe even better than we actually know ourselves. That might sound crazy, but consider this statement from a recent article, “The Rise of the Weaponized AI Propaganda Machine” [i] where an analytics firm compiled data on Facebook likes and built millions of consumer behavior profiles, subsequently fed into an AI political campaigning machine:

“With 300 likes, Kosinski’s machine could predict a subject’s behavior better than their partner. With even more likes it could exceed what a person thinks they know about themselves.”

Whether you buy this or not, the fact remains that consumer profiles are becoming richer and consumer behavior predictions more accurate.  Data are exploding, as are the algorithms voraciously feeding on them.

Brands compiling this data and wielding their algorithms do it because they say they want to know us better.  Presumably, this enables them to continuously add value, deliver insights, help automate our lives, and make attractive recommendations.

Ostensibly then, for consumers, it comes down to a few simple questions:

  • How much is our data worth to us?
  • What’s the value of the insights that brands provide when they use our data?
  • Are we getting an equitable exchange?
  • Can we trust brands to honor their commitments regarding the use of our data?
  • Do we understand the fine print in those agreements?

Consider the mission statement for Datacoup, a data company based in New York, who have gone one step further and are trying to make a marketplace where consumer’s have a more direct exchange of value for their data:

“Our mission is to help people unlock the value of their personal data. Almost every link in the economic chain has their hand in our collective data pocket. Data brokers in the US alone account for a $15bn industry, yet they have zero relationship with the consumers whose data they harvest and sell. They offer no discernible benefit back to the producers of this great data asset – you.”[ii]

So are you getting value for the data you’re giving up?  Are the “Prescriptions” you get in return an equitable exchange?  Are you aware of what happens to your data after you release it?

A Day in the Life of Your Data

We all joke about the eye-glazing 56 page “Terms and Conditions” from Apple that we always accept and never read.  We want the free software, and don’t worry about the consequences. However, if you use that approach for everything you do online, that mindset is dangerous.

Consider this for a moment.  Most firms have language that allows them to send your data to affiliates, which is a fancy word for other companies. Once floating in the ecosystem, it’s grinded, distilled, and appended to other copies, until records of your preferences, habits, and behavioral are expressed in 5,000 or more different ways.  If it’s wrong, it doesn’t matter, because you don’t own it, don’t have access to it, and can’t change it.  In many ways, it’s another version of you, right or wrong.

Is Prescriptive AI Working?

So back to the question of whether it’s helping.   It’s fair to say there are cases where it adds value.  Here are some examples:

  • You decide you aren’t satisfied with your telecommunication services. You’ve made it obvious (with various signals) you’re considering other alternatives.  Your current provider prescribes an attractive bundle that satisfies your needs. You get a better bundle of services, and your provider retains you.  The bundle is custom tailored for you, using AI.
  • You have investments with a firm. You provide additional data on your financial goals, risk tolerance, and other investments, and they provide advice (prescriptions) on how to achieve your goals over time, within the parameters you set.  They provide various alternatives and education that prove useful to your financial planning.   Presumably, some of those alternatives include additional investments with them, and turn out to be good choices.
  • Your health plan suggests meaningful diet, exercise, and other tips that promote a healthy lifestyle. They are custom tailored to you, based on your family history, age, and other personal data you provide.   They reward you with lower premiums or credits.

These are just a few examples, and many more exist across industries such as travel and leisure, automotive, insurance, and retail.  And while good exchanges do exist, there are plenty of examples where the prescription doesn’t justify the information surrendered because the value exchange is unbalanced, or the prescriptions are ineffective.

Final Thoughts

In her book, “Weapons of Math Destruction[iii],” Cathy O’Neil writes:

“Many of these models, like some of the WMDs we’ve discussed, will arrive with the best intentions.  But they must also deliver transparency, disclosing the input data they’re using as well as the results of their targeting. And they must be open to audits. These are powerful engines, after all.  We must keep our eyes on them.”

She highlights important considerations we must heed.  I’m not convinced we’re spiraling toward a dystopian society regarding the use of prescriptive AI for customer engagement, but I do believe a balance is necessary between efficacy of these systems and fairness.  As responsible marketers, we should be mindful of the ramifications of the models we use for prescriptive purposes, and as consumers, it’s our job to demand transparency, choice, and a level playing field.

[i] Anderson And Horvath, https://scout.ai/story/the-rise-of-the-weaponized-ai-propaganda-machine, January 2017

[ii] Datacoup, https://datacoup.com/docs#faq, February 2017

[iii] Cathy O’Neil, 1st edition, Weapons of Math Destruction (New York: Crown), 2016.

3 Tips to Drive Business Value with CX – Fortified with REAL AI

With a first name of “Artificial,” AI has certainly entertained us with its virtual possibilities.  Stories of wholesale disruption by robots and fully automated lives make for good movie material, but as of yet, AI hasn’t dominated the marketplace, consumer experiences, or business applications in a monumental way.  AI has the potential to change our daily lives, yet for most, its impact so far has been nominal.

Real AI

As a businessperson concerned with driving better customer engagement, you’re no doubt interested in this topic, yet probably carry some healthy skepticism about the potential for return from your AI investments, and the risk of them failing.

Congratulations!  Your suspicion is not only natural, it’s warranted.  Here are three tips for how to maximize value from your AI investments, and minimize any risk of disillusionment.

1.    Provide predictions about Customer Intent

No doubt, you have scores of business intelligence systems that compile and codify data.  They provide customer profiles, program dashboards, and other scorecard reporting of historical results.  Although informative, these systems aren’t predicting anything.  As such, they are rear view mirrors, providing a view of the past, but not anticipating and generating ideas regarding courses of action that may lead to more optimal outcomes.

Any investment in AI aimed at improving customer engagement must include capabilities to predict customer motivation.   Why are they calling?  Are they already upset?  Are they highly likely to be shopping for another provider?  What product or service best suits their true needs?  How valuable is this customer over their projected lifetime?

Answers to these questions are always guesses, yet pragmatic AI systems today use proven statistical methods to minimize errors in predictions, calibrate themselves with feedback loops, and provide confidence intervals so users understand their range of applicability.

For example, it’s feasible today to have a portal providing your marketing employees with accurate predictions such as:

  • Customer value
  • Churn likelihood
  • Loyalty to brand

 

For service agents, predictions like:

  • Customer sentiment
  • Reason for calling
  • Nature of problem

 

For sales personnel:

  • Price sensitivity
  • Available budget
  • Perception of value

 

Effective AI has to improve your ability to understand what impels your customers to behave the way they do, or the way they may act in the near future.  Work backward from these insights, and demand that your AI systems and vendors can prove they have experience extracting insights from available data, and in predicting and surfacing these items.

2.    Make dynamic suggestions to better serve the Customer

Consumers do business with brands that provide repeatable value.  That value comes from not just positive product use, but also from an enjoyable and smooth buying process, a friendly and efficient on-boarding experience, and stellar service.

As consumers experience a brand during those journeys, they rack up the score, keeping tally of the relevance and effectiveness of the systems and people they encounter along the way.

Any AI system worth its salt should provide ranked suggestions either directly to customers, or to customer facing employees such as:

  • Next Best Offer: The most relevant product needed, and an individualized incentive on it that will be both compelling, yet still economically affordable to the business.
  • Next Best Service Action: The best thing an agent can do next to maximize the chance of reaching an effective and efficient solution to the service problem at hand.
  • Next Best Sales Activity: The best action for a salesperson given available leads, accounts, contacts, and opportunities.

For the marketers responsible for providing next best offers, AI systems should help them recognize buying patterns, automatically perform tests, filter out offers that don’t apply, and statistically rank the best content & promotions for the right individuals.  AI should even suggest the best timing for those recommendations.

For service workers, AI should deflect routine service requests to automated or self-service channels, guide agents on complex service cases, surface potential solutions to issues, and help gauge the sentiment of the customer during the process.

For salespeople, AI should predict the best contacts to engage with in an account, the activities most likely to move an opportunity to the next sales stage, and which accounts to spend energy on to maximize close rates and quota attainment.

3.    Install a system that learns in Real-Time

Your world changes every day.  As a professional, you wake up every day to news of competitive threats, new opportunities, and market conditions that vary the effectiveness of the strategies you employed yesterday.

If you were slow to react, or simply ignored these factors, you’d fully expect your overall business performance to degrade, so you listen carefully to these environmental conditions, and you adjust accordingly.

Think about your AI systems the same way.  They must include adaptive mechanisms, where recommendations made are monitored, in real-time, and dispositions are fed back into the machine, so it can learn from its success and mistakes.   Marketing, service, and sales systems receive feedback constantly in the form of customers either ignoring your treatments, or responding to them, so ensure your AI system uses them.  Your AI system should rapidly improve its performance, as it’s fed more data, and as it tunes itself.  If it’s not, after a short trial period, start asking some hard questions to your provider.

Make sure your results (even if delayed), are monitored, measured, and understood. An accurate measurement of the real business value from AI comes when you understand the baseline, and can measure the lift you get when you employ the insights and recommendations delivered by AI.

Track response rates, conversion rates, incremental revenue, return on investment, and compare to what your vendor promised, what you expected, and what you need to achieve.

AI is a broad topic, yet to improve customer engagement and your outcomes, boil it down to these 3 things; understand customer intent, make relevant suggestions, and learn in real-time so your performance improves over time.   If you do these, you will realize REAL value from AI.

AI in CX: Real or Superficial Intelligence?

Artificial Intelligence

By all accounts, 2017 has ushered in the dawn of the newest Artificial Intelligence (AI) era. Most technology hype cycles follow typical paths, quickly shooting up, often followed predictably thereafter by a meteoric reentry to reality.  Typically, the entire flight takes place over a decade or so, as the fuel of inflated hype burns out, and the gravity of commercial application pulls down on its excitement to test its true value.

AI, however, seems different. It has appeared, drew much fanfare, and then disappeared several times already – more akin to a comet, flaring a tail of excitement with each new orbit.  As it reemerges, nearing the heat of expectation once again, it lights up with a spectacular plume, flung into space for another long dark hiatus.

AI history suggests five such orbits already – so is it destined for cold dark space soon?

Superficial AI

Regardless of the metaphor du jour, what we must inspect is the true value returned today, not the imagined expectations of tomorrow. The best test of commercial viability is not an intelligence test; it’s whether consumers are getting more value, and if the business offering the products & services are using AI technology as leverage, providing those things with higher margins.

For example, my mobile device is now my phone, my Garmin, my camera, my alarm clock, my digital assistant, my video recorder, my dictation device, my virtual reality device, and so forth.  20 years ago, it might have cost me $5,000 for these services.  Today, I get it all for $500 – $700.

We’re all under pressure to do more in the same amount of time.  To that end, these devices have become indispensable – they are essential to modern day survival – adapt to them, use them efficiently, or you’re passed by.

Therefore, by some measures and definitions, AI has delivered this time around.  Personally, I don’t care when a big company announces their sixth AI acquisition, or what their advertisements or creative animations say.  In my view, the proof is if customers are buying, are satisfied with those purchases, and are reporting their lives are easier, more productive, and more enjoyable.

Businesspeople must apply the same tests.  Can they deliver better customer experience with AI?  Are their product & services measurably smarter and more efficient?

If they aren’t passing those tests, then it’s just superficial AI.

Real AI Value in CX

AI – Automated Intelligence

As we all admire the latest bright tail of inflated expectation, let’s study what AI has really contributed to delivering better customer experience (CX) this time around.

For starters, look again at that magical device, the smartphone.  It streams location data, activity levels, browsing preferences, timing behavior, and the like.  Businesses consume this contextual data, and use decision hubs infused with AI algorithms that in less than a second calculate a next best action or insight.  That’s real!   Big banks, telecommunication / technology firms, and retailers are doing this today to improve acquisition, on-boarding, cross selling, and retention rates.

For consumers, the insights automatically delivered include recommended products, drive time estimates, calendar reminders, and service alarms. Alerts & notifications remind when bills are due, when fraud occurs, or when more exercise is required to meet goals.  Cars drive & park themselves, thermostats learn, and media services understand consumer preferences.   Customers can interact with machines by simply speaking to them.

For the marketers responsible for engagement strategies, AI now recognizes buying patterns, automatically performs A/B and multi-variate tests, which ranks the best content & promotions for the right individuals, and even suggests the best timing for those recommendations.  For salespeople, AI predicts the best contacts, opportunities, and accounts to spend energy on to maximize close rates.  For service workers, AI deflects simple service requests, and guides agents on complex service processes to improve time to resolution, ultimately improving customer satisfaction.

Simply put, there can be little argument that AI has delivered value during this orbit, much of it in the form of automation as opposed to higher-level intelligence.  Fewer marketers deliver more relevant and better-timed tactics.  AI assisted sales means higher quality pipeline with sharper close rates. Contact center managers relish shorter handle times and more efficient call resolution with less staff, and consumers enjoy shorter wait times and voice / bot-assisted service. For those using AI, NPS and customer satisfaction scores are on the rise.

All of these outcomes are commercially feasible.  Every business (not just the avant-garde) must rapidly incorporate these proven technological capabilities.  Hesitate, and the likely result will be eventual irrelevance.

What’s next – In my lifetime?

With all this said it’s back to our question.  Can AI keep delivering, or is it bound to let us down soon?

As humans, we love to dream.  That’s important.  In fact, regardless of how fast machines move forward, it’s still something that separates us from them.   We envision a fanciful future, and plot our course toward it.  Along the way, we stumble, get humbled, get up, and plot again.  This is our nature.  Each step along this evolutionary path, we create and refine machines that help us achieve our dreams.

Our vision seems unchanged.  We long to make life easier and more enjoyable for more of us.  To do this, we must continue to refine our existing tools, and invent new ones that assist us, and make up for our physical and human limitations.  No different from our first instruments, modern day smart tools take over tasks we were never very good at, or simply couldn’t do. They help feed us, optimize our resource consumption, and make our very survival possible.  We are already dependent on them, and there is no turning back.

This is also true for customer experience tools.  Our expectations are high and climbing.  We expect to interact with brands that listen, understand our preferences, react accordingly, and when something goes wrong, can turn on a dime and make things right instantly.

When I enter a website, I expect the search to be intelligent, the user experience to be delightful, and the checkout process to be flawless.  If I chose to do all this while mobile, I expect the same experience on my smartphone.  If I need help, my first reaction is, “why did things go wrong in the first place…how could this have been prevented,” and then I test if resolution comes fast with low effort – and does the business learn from the mishap.

This is the new normal.  Unfortunately, many brands today are not delivering on this type of customer experience.  The bar is high, but the elevation of game is not so much a demand from technology as from organizational re-tooling and reorganization to accommodate for technologies already commercially available.

Technological advancements will continue to accelerate.  Smarts will show up in more devices. We will demand our machines become more human, especially in delivering customer service and better experiences.  As humans, we love a personal touch, a social exchange, a sense of community and belonging.  So far, machines have not been able to deliver on any of these aspects.  That’s changing.

Presently, there is very interesting research going on to bring more human-like aspects to machine interactions. Google’s DeepMind research lab has made impressive gains in speech synthesis (text-to-speech) in a project known as “WaveNet” where robotic voices are becoming a lot less robotic.  Similar advances in Chabot research is leading to smarter bots able to remember details, learn right from wrong answers, and hold basic conversations.  You can try one of the better ones at http://www.mitsuku.com/

These developments are exciting.  The possibilities are enormous.  Yet until these become commercially viable and noticeably better with true customer engagements, you should train your eyes on what is real in AI today.  For now, focus your investments and efforts on delivering real CRM value from AI tech today in the form of things like simple service request deflections, intelligent routing to the right agent, relevant product recommendations & next best offers (based on individual behavior profiles), and guiding salespeople with next best activities.

Meanwhile, keep close tabs on these other AI CX innovations as they progress, take some calculated risks on a few promising areas, and prepare for the next revolution of AI.  The AI comet will be back shortly.