Telecom Customer Churn Prediction Using Supervised Machine Learning Techniques

Abstract

In today's time, customer churn is one of the major issues in many large-scale industries. Because it has a direct impact on the company's revenue, it is necessary to find a solution to determine which customers are most likely to churn so that large-scale companies can make wise decisions and take steps to deal with customer churn. Customers may leave for a variety of reasons, but the most common is that they are dissatisfied with the services provided by the companies. In this proposed solution, we will be building a machine learning model that has the capability to predict the potential churn so that the Telecom companies can make proper marketing retention strategies as time passes. In this system, we will be using existing datasets and necessary pre-processing techniques like bivariate and univariate analysis, further using data visualisation to understand the dataset properly. After this, we will be building different classification models by applying and comparing different supervised machine learning algorithm such as the Logistic Regression, the Support Vector Machine algorithm, Decision Tree Classifier, and the Random Forest algorithm . The best machine learning algorithm is chosen by using performance metrics like accuracy, F1 recall and so on.