Three Categories Customer Churn Prediction Based on the Adjusted Real Adaboost

Abstract

It is necessary for enterprises to establish a customer churn management system. In this article, we take the heterogeneity into consideration and divide the churn people into two classes according to the data characteristics. Moreover, we try to modify the bias of multi-class unbalanced data classification. Then we propose a new method based on Real Adaboost for the problem. The proposed method takes the within-group error into consideration and creates another view of reweighing the cases. Empirical study on our sample data shows that the new method performs better than the other method.

Keywords:

• Churn prediction
• Customer heterogeneity
• Real adaboost
• Unbalanced data

Mathematics Subject Classification:

• Primary 62-XX
• Secondary 62H30

Acknowledgments

This work was performed in the Project “The Study of Service Context Prediction Theory and Key Technologies based on Human Cognitive Mechanism” (No. 60802034) supported by National Natural Science Foundation of China and Specialized Research Fund for the Doctoral Program of Higher Education (No. 20070013026) and Beijing Nova Program (No. 2008B50). This work was also supported by National Natural Science Foundation of China (No. 10701079 and No. 11071253).