Predictive Model for Cutting Customers Migration from banks: Based on machine learning classification algorithms

Customer satisfaction is one of the most important factors that lead banks to success, and it can be said that outcome profits are depending on having more and more new customers. In in the operational environment it may happen to face some issues that make banks lose customers, which is bad because of the proper actions that would be taken from central bank for that performance. In this work we have used a free source dataset of bank customers' information, in order to build a model using machine learning classification algorithms such as; Decision Tree, Random Forest, Naïve Bayes, K Nearest Neighbor and Logistic Regression. The model evaluated using different measures depend on confusion matrix, and the results gave a high accurate level in predicting the customers who is going to leave the bank. This work would be a new step to keep customers interacting with their banks and stop their exiting by studying the reasons that causes this problem, which in turn increases the level of performance and profit.