The Analytics Capability Retailers Don’t Know They’re Underusing

Machine Learning and Data Science

The Analytics Capability Retailers Don’t Know They’re Underusing

I recently attended Shoptalk 2019 in Las Vegas, a trade show where retail executives come to network and discuss new industry trends, technology, and innovation. Between the insightful discussions, learning sessions, and keynotes, there was a technology trend that stood out to me.

Retailers are entering a new era of artificial intelligence (AI) and machine learning (ML). A couple of years ago, retailers were just beginning to notice and look into these technologies as “the latest shiny objects.” They now firmly understand the value and need for AI and ML. The next step for retailers is implementing practical applications of these technologies that align with their objectives. Notably, there were some in-depth discussions about how to apply AI and ML to customer personalization.

Personalization is a critical part of the retail customer experience. Your customers don’t want to feel like cogs in a machine or just another face in the crowd — they want to know, without a doubt, that you value them, and their business. This is where customer cluster analysis — a key capability of ML- and AI-powered solutions like prescriptive analytics — comes into play. Essentially, cluster analysis allows you to break down your customers into groups, or clusters, based on similar behaviors and characteristics (not just hard attributes like gender, zip code, and others). From there, you can use this information to personalize the customers’ experience based on the parameters of their clusters, such as their favorite product attributes, loyalty, average basket size, and others.

Advanced cluster analysis is a remarkably useful capability of ML and AI — and yet it’s underused. At ShopTalk, many retailers talked about how they had access to machine learning cluster analysis, but were using it to cluster their customers not by their shopping behaviors, but by their demographics, such as age, location, or household size. This is a huge miss.

In my experience, clustering by demographic tells you little, if anything, about how to personalize the customer experience (or how to encourage customers to spend more). Brendan Witcher, a Forrester Research expert on digital business strategy and customer engagement, put this difference well at the private dinner event Profitect hosted at ShopTalk: “As retail customers, are you all the same or are you uniquely different?” he asked the room. “We might all be between the ages of 30 and 40 here, but does that really mean we’re buying all the same products?”

Of course, the answer is no. The fact that you live at zip code 54987 doesn’t mean you behave, purchase, and feel the same way as your neighbors. There are countless characteristics beyond demographics that influence customer shopping behaviors, which can tell you much more about what these customers expect from a retail experience. For example, imagine a promotion on children’s jeans, which you send as an offer to a cluster of customers with children.

That sounds logical, but there’s more to consider. Those customers may have kids, but that doesn’t necessarily mean they need, like, or want jeans. What if half of those customers’ kids attend private schools that require khakis or skirts? What if a large chunk of the kids are girls who prefer dresses? Either way, numerous customers will receive a promotion that doesn’t fulfill their needs. Not good for personalization or targeted promotions.

In the above scenario, it would make more sense to characterize customers by typical buying patterns, and send the promotion to those who buy the most children’s jeans, or used to buy but stopped for some reason. Customers would receive more relevant promotions, and their experience would feel personalized. It’s a huge opportunity for a big win with any retailer.

As a real-life example, a Profitect customer, a large general retailer, had a popular loyalty program based on spend amount, but lacked the technology to offer personalized promotions to each loyalty tier. Our customer’s marketing department could only use blanket marketing across the entire loyalty program — which meant they gave discounts to people who would have paid full price anyway. The retailer approached Profitect and adopted our Marketing module to get better visibility and control over its promotions.

The retailer now uses the Profitect Marketing module to monitor customers’ statuses within the loyalty program. The module sends prescriptive actions to the marketing team whenever a group of consumers is about to qualify for a higher tier, directing them to send the customer targeted promotions based on their typical buying-pattern behaviors. These promotions entice the customer to make enough additional purchases in the categories they like and need to push them over the threshold to the next loyalty tier. Since adopting the Marketing module, the retailer’s top-tier loyalty members have increased significantly. Because upper-tier customers are more likely to not just spend more money, but also promote the brand to others, the retailer has also seen an overall sales increase.

With Profitect’s prescriptive analytics solution, our customers can cluster their shoppers with a variety of behavioral parameters. Some of their favorites include average basket size, product-return preferences (i.e. do they prefer to return e-commerce products via mail or in stores?), loyalty ranking, typical purchases, and frequency of visits. If they desire, our customers can also cluster by general demographic information, such as household size, zip code, etc.

If your retail or CPG organization is interested in improving your customer experience while also strengthening profits and margins, reach out to us at Our solutions experts are eager to help you achieve your most ambitious goals.

Leave a Reply

Your email address will not be published. Required fields are marked *