10Indonesian Journal of Electrical Engineering and Computer Science Vol. 26, No. 1, April 2022, pp. 539~549 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v26.i1.pp539-549  539 Journal homepage: http://ijeecs.iaescore.com Predicting customers churning in banking industry: A machine learning approach Amgad Muneer 1 , Rao Faizan Ali 1 , Amal Alghamdi 2 , Shakirah Mohd Taib 1 , Ahmed Almaghthawi 2 , Ebrahim Abdulwasea Abdullah Ghaleb 1 1 Department of Computer and Information Sciences, Faculty of Science and Information Technology, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia 2 Department of Computer Science and Artificial Intelligence, College of Computer Science and Engineering University of Jeddah, Jeddah, Saudi Arabia Article Info ABSTRACT Article history: Received Jul 15, 2021 Revised Jan 30, 2022 Accepted Feb 7, 2022 In this era, machines can understand human activities and their meanings. We can utilize this ability of machines in various fields or applications. One specific field of interest is a prediction of churning customers in any industry. Prediction of churning customers is the state of art approach which predicts which customer is near to leave the services of the specific bank. We can use this approach in any big organization that is very conscious about their customers. However, this study aims to develop a model that offers a meaningful churn prediction for the banking industry. For this purpose, we develop a customer churn prediction approach with the three intelligent models random forest (RF), AdaBoost, and support vector machine (SVM). This approach achieves the best result when the synthetic minority oversampling technique (SMOTE) is applied to overcome the unbalanced dataset and the combination of undersampling and oversampling. The method on SMOTED data has produced excellent results with a 91.90 F1 score and overall accuracy of 88.7% using RF. Furthermore, the experimental results show that RF yielded good results for the full feature-selected datasets. Keywords: AdaBoost Banking industry Churning Random forest SMOTE Support vector machine This is an open access article under the CC BY-SA license. Corresponding Author: Amgad Muneer Department of Computer and Information Sciences, Universiti Teknologi PETRONAS 32610 Seri Iskandar, Malaysia Email: muneeramgad@gmail.com 1. INTRODUCTION Every day there is much competition growing in the banking industry [1]. Thus, if any bank wants to increase its market share by acquiring new customers, it must follow customer retention strategies. It is shown that improving the retention rate by up to 5% can increase a bank’s profit by up to 85% [2]. Different banks offer attractive plans like internet banking, mobile banking, debit card, credit card, savings accounts with nil balance, credit points based on the usage of the customers [3], best plans for various loans like education loan, housing loan, agricultural loan, vehicle loan, mortgage loan, and startups loan. In the group of all these facilities or plans, crediting a loan to a customer is a critical task because, in this case, each bank has to analyze the customer's capacity prior to offering that loan [4]. To complete the crediting loan process to customers, there are a number of banks that have decided to incorporate a credit card scheme that will ensure that whenever a customer applies for a credit card, his or her ability to avail of the card will be evaluated. Many banks initiate the request for providing credit cards to new customers based on their credit points [5]. However, there will be multiple opportunities for clients to churn out of a particular bank for every customer