Telecom Churn Prediction using Machine Learning
1 Data Science and Engineering. Birla Institute of Technology and Science, Pilani (UCG, ACU, AIU Affiliated), India.
2 Lecturer in Computer Science, SKR &SKR GCW, Kadapa, Andhra Pradesh, India.
3 Maturi Venkata Subba Rao Engg. College, Hyderabad, Telangana, India.
Research Article
World Journal of Advanced Engineering Technology and Sciences, 2022, 07(02), 087-096.
Article DOI: 10.30574/wjaets.2022.7.2.0130
Publication history:
Received on 14 October 2022; revised on 22 November 2022; accepted on 25 November 2022
Abstract:
In every industry, customers are crucial. Customer churn can have a variety of effects and have a negative influence on sales. Analysis and forecasting of customer turnover must be a key component of any business. We will analyze and forecast customer turnover in the telecom industry in our study. The study of consumer behavior is crucial for the telecommunications sector in order to identify those customers who are most likely to cancel their subscriptions. Because there is so much data available and the market is becoming more competitive, businesses are spending more time trying to keep their present consumers than they are trying to win over new ones. The mobile telecommunications market recently transitioned from being one that was expanding quickly to one that was saturated. The goal of telecom companies is to refocus their attention away from attracting new, huge customers and toward retaining existing ones. Knowing which clients are likely to switch to a competitor in the future is important for this reason.
Using machine learning techniques such as Decision Tree, Logistic Regression, Random Forest, Gradient Boosted Machine Tree, and Extreme Gradient Boosting, the model is proposed for churn analysis and prediction for telecommunication firms. The performance of various models is also compared. On the basis of the supplied dataset, comparisons are made on the algorithm’s effectiveness.
Keywords:
Machine Learning; Variance Reduction; Prediction; Classification; Telecom; Churn; Logistic Regression; Bayesian Models; Random Forest; Gradient Boosted Machine Tree; Decision Tree
Full text article in PDF:
Copyright information:
Copyright © 2022 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0