Application of Data Analytics Techniques for Predicting Customer Churn

Abstract

This paper deals with the classification of bank customers based on their characteristics. The aim of this research is to provide an optimal model capable of identifying customers who plan to leave the bank in the near future and switch to competitors. Identifying the customers is crucial because it allows you to allocate funds to marketing more efficiently and ensure competitiveness. As part of the paper, the data were first adequately pre-processed, which was followed by the compilation of eight classification models. These models were then divided into two groups according to the approach to solving class imbalances in the target attribute.