CHAMP: A Prototype for Automated Cellular Churn Prediction
Data Mining and Knowledge Discovery
Computer assisted customer churn management: State-of-the-art and future trends
Computers and Operations Research
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
As customer churn has become a critical business issue for most mobile telecommunications providers, predictive modeling based on knowledge discovery of data mining is an approach being used to facilitate customer retention more effectively and proactively. This paper reports a preliminary study of applying data mining to solve a real-world customer attrition problem. It uses customer information to make predictions about the likelihood of churn. The target rate is very small, around 0.5% monthly churn rate. Nevertheless, by scrutinizing data to extract a large number of independent variables and by using a large training data set, the predictive model delivers excellent performance in field test. Issues in the practical application of data mining are also discussed.