CHURN PREDICTION AND CLASS IMBALANCE FOR DATA MINING PROBLEMS

Abstract

Customer churn and engagement has become one of the top issues for most banks. It costs significantly more to acquire new customers than retain existing ones and it costs far more to reacquire defected customers. In fact, several empirical studies and models have proven that churn remains one of the biggest destructors of enterprise value for banks and other consumer intensive companies. Churn has an equal or greater impact on Customer Lifetime Value when compared to one of the most regarded KPI’s (Key Performance Indicator) such as ARPU (Average Revenue per User). The quality of service and banking fees seem to be the top two drivers for customers to consider another alternative.