Application of Machine Learning to Customer Churn Risk Prediction

Abstract

Accompanied by technological globalization and upswing of telecommunication industry in the 21st century, the number of operators is springing up like mushrooms after rain in the market and that intensifies the industry competition environment due to the unprecedented growth trend and the challenges. As a research hotspot in the field of business analysis, prediction of customer attrition risk possesses some extensive range pertaining to applications within global marketing, telecommunications and other fields. Due to the complex relationship between customer information and the products used, it is difficult for merchants to conduct effective risk assessments. Nevertheless, customer churn risk prediction has made such rapid progress over the past few years with the development within computer science and machine learning so that the researchers would be able to establish more potential connections and achieve more accurate predictions about customer churn. This article summarizes customer churn risk prediction in the order of time and technology iteration, and mainly introduces 9 classic prediction methods based on machine learning. Additionally, four relevant performance measurement metrics and one data set are explored. Eventually, in view of the problems existing in the current customer churn risk prediction methods, prospects for future research are proposed.