Chapter 6 - Response Modeling in Direct Marketing: A Data Mining-Based Approach for Target Selection

Abstract

Increasing costs of direct marketing campaigns coupled with declining response rates have prompted many direct marketers to turn to model response behavior. In direct marketing, data mining has been used extensively to identify potential customers for a new product. Using historical purchase data, a predictive response model with data mining techniques is developed to predict a probability that a customer is going to respond to a promotion or an offer. The purpose of this study is to identify the bank customers who are more likely to respond positively to a new product offering. To achieve this purpose, a predictive response model was built. For the purpose of modeling customers’ data were gathered from one of the Iranian banks. RFM features and their two-way interactions were constructed. Feature selection was carried out to determine the inputs to the model. Also undersampling was used for solving class imbalance problem. Finally SVM was used as a classifier for classification purpose. The result indicates that the company can reach three times as many respondents as if they use no model for target selection and this could be very beneficial for the bank; it can maximize customers' response to a product offering, minimize the overall marketing cost, and improve customer relationship management.