Predictions of Customer's Churn in Telecommunication Industry Network Area using Machine Learning (ML) Algorithm

Customer churn, the loss of customers over time, poses a significant challenge for businesses across various industries. Early detection of at-risk clients enables focused actions, which in turn increases profitability and customer retention. Customer attrition is a persistent problem in the telecom sector due to intense competition. The goal of this paper is to protect revenue streams by using Machine Learning (ML) to forecast client attrition and enable tailored retention measures. Over the last ten years, various ML and data mining strategies have been published in the literature to forecast consumer churners using heterogeneity customer datasets. This paper provides an overview of the Customer turnover problem and investigates the application of different ML approaches, such as XG Boost, Gradient Boost, AdaBoost, ANN, and logistic regression, to predict customer turnover and compare the model effectiveness in terms of accuracy.