Predicting Credit Card Customer Churn Using Support Vector Machine Based on Bayesian Optimization

Abstract

In this study, we have employed a hybrid machine learning algorithm to predict customer credit card churn. The proposed model is Support Vector Machine (SVM) with Bayesian Optimization (BO). BO is used to optimize the hyper-parameters of the SVM. Four different kernels are utilized. The hyper-parameters of the utilized kernels are calculated by the BO. The prediction power of the proposed models are compared by four different evaluation metrics. Used metrics are accuracy, precision, recall and F1-score. According to each metrics linear kernel has the highest performance. It has accuracy of %91. The worst performance achieved by sigmoid kernel which has accuracy of %84.