RFM Variables Revisited Using Quantile Regression

We revisit well-known variables for database marketing/CRM and relationship marketing using a new methodology: Binary Bayesian Quantile regression. This method allows for a more thorough investigation of the relationship between the response variable and the covariates. The main conclusion is that taking intentions as a proxy for real churn behavior yields biased results because the effects are differentially inflated across quantiles. Moreover, effects are shown to differ relative to the median effect resulting in even more inaccurate information for marketing decision making. This study clearly demonstrates that marketing practitioners can benefit from using quantile regression and shows the importance of obtaining and analyzing real observed behavior.