Abstract Customer churn analysis and prediction in telecom sector is an issue now a days because it’s very important for telecommunication industries to analyze behaviors of various customer to predict which customers are about to leave the subscription from telecom company. So machine learning techniques and algorithm plays an important role for companies in today’s commercial conditions because gaining a new customer’s cost is more than retaining the existing ones. This project focuses on various machine learning techniques for predicting customer churn through which we can build the classification models such as Logistic Regression, Random Forest and lazy learning and also compare the performance of these models.

Keywords— churn , machine learning , Logistic regression , Random Forest , K-nearest-neighbors

| DOI: 10.17148/IARJSET.2021.8692