We all know that the data science has been flourishing and changing faces of all imaginable worlds. We’ve seen AI create paintings and music, we’ve seen it drive cars, we’ve seen it diagnose illnesses, and these are just the most obvious, fancy things. Small irrelevant questions, like “What will Susan buy in a supermarket tomorrow?” seem so non-futuristic and so ‘80s. Customer behavior did, indeed, start off with simple product ranking and customer-similarity solutions.
But that was in the ‘80s. Since then so many smart people have been working for decades, and in shadow of other flashier AI achievement, they have created models and tools, which can simulate future customer behavior and reactions in disturbingly high resolution.
Don’t be fooled, maybe it starts with Susan buying a detergent tomorrow but customer behavior is how corporations are built, elections won, and migrations triggered. No intention to start a conspiracy theory discussion here.
So the question is – why and how do we model customer behavior? Let’s go over some basics. Classic ML algorithms by their definition try to find patterns in data. Ask a question, define a target variable that describes it, define features (or don’t if you want to go deep) and then tune, tune, tune. When it comes to product recommender systems, we rely on the past behavior and choose some of the wide variety of available solutions, like collaborative filtering or behavioral models or classifiers or any combination of them. No matter what you are selling, in order to make your customers buy more you need to understand them first, otherwise, why bother. Understanding their behavior it in order to change it, and, unless you are clairvoyant, you don’t have the data with patterns of changes you are about to cause. That takes us to the exciting world of experimenting. It all started very reasonably and transparent, people have been doing A/B testing since forever. The digital marketing era widened the playing field. It’s not about which actor you want to see on a billboard any more, it’s about campaign scheduling, and background colors, and language of the text, and the delivery channel… the number of variables just kept growing so people remembered a thingy called Multi-Armed Bandit, which is a very neat solution for handling high number of experiments. With the number of experiments constantly growing, digital marketing opened another door, called personalization. Obviously when it comes to marketing, one message doesn’t fit all. In theory, we have the means to send each person a tailored message that will make her/him a loyal customer. Some things are easy to personalize, like the discount level for customers with high risk of churning. You don’t have to reduce your profit by giving everyone a huge discount, you can calculate how much would be the sufficient minimum for each customer. Some other things are more challenging, for example, we can’t push creative guys in our design department to come up with thousands of unique banners. We will have AI doing that soon, but while we wait for AI to become very good at creating banners on demand, the middle ground has to be the segmentation. Luckily, the existing algorithms are very good at clustering, i.e. grouping similar elements and creating groups that differ one from another. Voila, now the designers need only to come up with 5-10 different sales stories, according to descriptions of target audiences that machine gave them, and the machine will take care of the rest – what to show to whom, when and where. While it always starts with whether Susan will buy the detergent tomorrow, we can now persuade Susan to buy more expensive detergent, or even stop using detergent, or persuade her to go save dolphins (no offence to dolphins).
The moral of the story – even though we all like to think we are special, aware of influences and grounded with our principles, the numbers say we are not, at least on average. And in order to increase your sales, the average is all you need.
Having said all this, what did we do about it? Over the years of work with clients, we have realized that the requirements keep repeating, regardless of the industry. Every company wants to know the same thing – how to optimise (increase) the revenue. This goal requires answering to a number of typical questions: What do customers want/need? What is going to be their next purchase? What to offer/recommend them? How to talk to them? Which customers are about to churn? How to prevent churn? What could be the next good product?… just to name a few. And, what is more, those questions often need to be answered at the very low level, sometimes even for an individual customer.
Almost every company/brand possesses data about their customers to be learned from but very few are in position to hire an in-house data-science team, or pay for the extremely expensive (and complex) customer analytics software. This is why JourneyTree tool was created in the first place, to provide a low risk approach for every company to explore their data, estimate its value (knowledge that can be extracted) and decide on the future strategy regarding customer analytics. All without huge commitments and investments, by means of time, resources and effort. The goal is to provide a solution for companies that would like to get a taste of Customer Analytics in the simplest and the quickest way, but still providing actionable information!
Find out more at journeytree.io