The Secret Sauce for B2B Loyalty Marketing
The following is the efficiency curve of one of the resultant models:
This is a typical way of measuring the predictive power of the model in terms of “cumulative gains” realized by the exercise. Here, the top model group displays an over four-times gain in terms of loyalty measurement over general population, while the tail-end of the curve indicates “not-so-loyal” or “vulnerable.”
Could this model have been more effective with more colorful sets of input data? Yes. Would it have changed the way marketers would line up their customers in terms of loyalty proxy in a significant way? Not really.
That is why moving quickly with readily usable data is important. Models can improve, but generally speaking, rankings do not shift drastically. In other words, some company that scored three or four on the loyalty scale won’t jump up to the top group just because some new type of data got introduced into the mix.
So what did we recommend after this type of exercise?
- Now that we have proxies of loyalty (not carved in stone, but proxy scores for everyone in the base), marketers can engage “likely to be loyal” customers (generally the top two to three model groups) with special care, more proactively.
- At the bottom end of the curve (generally the bottom three to four model groups), identify “valuable, but vulnerable” customers by combining the loyalty model score with present value — or preferably, a separately developed customer value model score. Then proactively treat those valuable-vulnerable customers to prevent churn.
- Test, test, test. Modeling is an iterative exercise. Set up control groups for a “no-treatment” segment, and continuously measure the effectiveness of prediction. Tweak the models periodically, and enhance them over time by adding other available data.
All of this is just “one” of the many possible ways to create proxies of loyalty. Without a doubt, depending on the business model, immediate challenges, channel usages and available data, the definition of loyalty and subsequent modeling exercises can take dramatically different forms.
Regardless, modeling is useful for maximizing the power of available data. The key takeaway here is that marketers must start small with readily available data assets, and take a gradual approach to improve them over time. In the end, it is not about the most mathematically sound models, but about treating customers properly in the order of importance to your business. For that, some proxy scores in your hand now will be much better that a perfect set of data that may never come.
Stephen H. Yu is a world-class database marketer. He has a proven track record in comprehensive strategic planning and tactical execution, effectively bridging the gap between the marketing and technology world with a balanced view obtained from more than 30 years of experience in best practices of database marketing. Currently, Yu is president and chief consultant at Willow Data Strategy. Previously, he was the head of analytics and insights at eClerx, and VP, Data Strategy & Analytics at Infogroup. Prior to that, Yu was the founding CTO of I-Behavior Inc., which pioneered the use of SKU-level behavioral data. “As a long-time data player with plenty of battle experiences, I would like to share my thoughts and knowledge that I obtained from being a bridge person between the marketing world and the technology world. In the end, data and analytics are just tools for decision-makers; let’s think about what we should be (or shouldn’t be) doing with them first. And the tools must be wielded properly to meet the goals, so let me share some useful tricks in database design, data refinement process and analytics.” Reach him at firstname.lastname@example.org.