Bank customer churn prediction based on transaction behaviour

Abstract

Customer churn has become a huge problem in many banks because it costs a lot to acquire a new customer than retaining an existing one. Possible churners in a bank can be identified with the use of a customer churn prediction model and as a result the bank can take necessary actions to prevent those customers from leaving the bank. In order to set up such a model in a bank, few things have to be considered such as how a churner in a bank is defined and which variables and methods should be used. This proposes that a churner for that bank should be defined as a customer who has not been active for the last three months as per the bank’s definition of an active customer. Behavioral and demographic variables should be used as an input for the model and classification should be used as a technique.