Churn prediction using comprehensible support vector machine: An analytical CRM application.

•Support vector machine (SVM) is made transparent by hybridizing it with NBTree.•Its effectiveness is tested on a medium scale unbalanced dataset related to bank credit card customer churn in analytical CRM.•Feature selection is carried out by SVM-RFE algorithm.•Proposed hybrid outperformed other techniques. Feature selection resulted in rules with short lengths and better comprehensibility of the system.•The generated rules act as an early warning expert system to the bank management.