An Advanced Analytic Approach for
Increasing the Value of Customer Retention
Bruce Ratner, Ph.D.
Database marketers are often tasked with holding customers in place as mature markets fizzle and new markets overtake existing ones. They use models as a key component in their marketing programs to make progress towards retaining a customer database. For example, in the financial services and telecommunications industries, database marketers use retention models to identify individuals who are likely to renew their credit cards and cellular services, respectively, and then develop campaigns targeted to those individuals intended to excite rather than cancel activity. The simple standard approach for building a retention model is to explain and predict a binary target variable - defined by renewers and non-renewers - using the logistic regression model. The purpose of this article is to introduce an advanced analytic approach for increasing the value of customer retention by using a bivariate target variable: revenue per customer and cost per customer. Building a model for a pair of variables requires an advance methodology (especially when the variables are not highly correlated). I discuss a real case study to compare and contrast the proposed advanced bivariate approach using the machine learning CPR Model and the standard approach using the logistic regression model with the single renew/non-renew target variable.
1 800 DM STAT-1, or e-mail at firstname.lastname@example.org.