Customer Churn Prediction

Abstract

Recently, in telecom industry every service provider wants to generate maximum revenue and is trying to provide the best services to its customers but here the main drawback is every company is providing almost the same services and being the customer, subscribing the service is the difficult task. For customers who have subscribed to a service, it is necessary for that service provider to keep a check on the customers if they are about to unsubscribe or remain subscribed. In this report, a model for customer churn prediction is proposed in which the user takes the customer train data and test data. Various algorithms are trained on the train data and applied on the test data. The accurate results are obtained which determines the churn predicted for the test data for each algorithm. This approach is implemented on the bases of Data Mining techniques in python language.