Combining Neural Network and Genetic Algorithm for Predicting the Churn of Bank Customers

This research proposes a hybrid model based on an artificial neural network and genetic algorithm to predict bank customer churn. After describing the details of data preprocessing, we present the proposed method with two variants. We compare it with state-of-the-art techniques such as the Support Vector Method (SVM), K-nearest Neighbours (KNN), Random Forest, and Logistic Regression. We also thoroughly analyze parameter settings to obtain the best neural network structure. For this purpose, we examine the effect of changing the number of neurons, the number of layers, and the network weights.