Predictive Marketing

Chapter 6Play Two: Predict Customer Personas and Make Marketing Relevant Again

As we saw in Chapter 2, clustering is the automated, machine-learning powered version of segmentation. Clustering is a powerful tool that allows us to discover personas or communities within your customer base. You segment customers to identify homogeneous groups that exist within your customer base, which can be used to optimize and differentiate marketing actions or product strategy.

An online retailer we work with is operating an e-commerce store where triathletes, hobbyists, and cyclists can celebrate and support their passions. The company wanted to cater to individual customer interests in a scalable and feasible way for its modest marketing team. It began by looking at the different personas that make up its customers and discovered certain distinct communities around its products: professional remote control racecar drivers; hobbyists building kits with their children; and remote control airplane enthusiasts. With this information, the company started to send out different newsletters to the different personas. Addressing each of these groups with meaningful personalized content immediately paid off: email click rates increased 66 percent. This is very typical, as we have seen similar increases in response with many companies we work with.

Clustering is a means to an end and it is a tool to develop strategies. Strategy informs segmentation and not the other way around. The three example schemas ...