Understanding customer behaviour by analysing customer data: An application of machine learning techniques in predicting Vietnamese customer churn in telecom industry

Abstract

The main goal of this study is to investigate the classification capability of several machine learning (ML) techniques, including decision tree (DT), Naêve Bayes, support vector machine (SVM) and logistics regression for predicting sub-scribers’ chum and retention in the growing Vietnam telecommunication industry. The application case is related to subscribers’ decision in the context of Vietnam. The results demonstrate that the logistics regression method obtained the highest performance with the corrected prediction percentage of 97.1429%. The findings also show that machine-learning techniques can be used to explicitly for solving Vietnamese subscribers’ churn in the telecommunication industry.