Identifying Potential Churners Through Predictive Analysis: Evaluation using Pro-Active-Attrition Management Logistic Regression

Abstract

Telecom industries are sensitive to customer churn prediction management system, which is popularly known as predictive analytics. Digital network and linked IT have severs that need customer churn prediction models. It is a great challenge for them to deal with a massive amount of data generated across fields. This research is a comprehensive study to develop a 'customer churn prediction model' by identifying potential churners using predictive analytics, concerning critical evaluation through pro-active-attrition management logistic regression. Such model and research work can help to identify customers, that are more likely to churn, save from fraudulent activities, inactive, or non-payment subscribers. The dataset is a scaled-down version of the full database generously donated by an anonymous wireless telephone company. There are 71,047 customers in the database and 75 potential predictors (total 78 variables) that combine the calibration and validation. Results show that the reason behind the customer churn is customer attrition.