Churn prediction in telecom sector using machine learning and neural networks.

Customer churn referred as customer who ceases his relationship with service provider. Customer churn analysis is performed to retain existing customers from churning. Churn prediction is gaining importance in telecom sector now a days because of its importance to analyze behaviors of different customers to predict who are in verge in leaving the subscription from service provider. Retaining existing clients is cheaper than gaining a newer one. This paper focuses on various machine learning and neural network methods to predict customer churn and identify the customers who are closer to leave their service from the respective service provider. Machine learning algorithms that are used to predict the customer churn such as Logistic Regression, Support Vector Machine, Random Forest, Adaboost and Artificial Neural Network. Data is collected from AT&T website and learning models are evaluated based on two criteria's i.e., Accuracy and Area under curve giving special weightage on Accuracy. Algorithm that proves to be the most accurate in all the test cases is compared and performance is measured. [ABSTRACT FROM AUTHOR]