Not too late to identify potential churners
Authors:
Open Access
- 6 December 2016
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 194-199
Abstract
Churn prediction, which is to identify who are prone to abandon the subscription, is of high significance for the operators to retain the potential churners. It should be noted that, in practice, the earlier the churners are identified, the more effective strategies the operators can develop to retain them. While the earlier prediction of customer churn in telecommunication industry has not been well investigated and the predicting accuracy of previous work degrades unacceptably when the interval between observed attributes and predicted labels is prolonged. In this paper, from a different perspective, we study the effectiveness to find the churners as early as possible with the accuracy being high enough, which we define as Early Churn Prediction. The predictive performance of the proposed model, which takes time series attributes and influence of churning contacts in social network into consideration, is investigated. We evaluate the method using a 12-month-long dataset collected by one of the largest operators in China. The results show that our model significantly outperforms the previous work especially when the prediction interval is larger than 3 months.Keywords
Funding Information
- Ministry of Science and Technology of the People's Republic of China (2014AA01A706)
- National Natural Science Foundation of China (61302077,61421061)
This publication has 18 references indexed in Scilit:
- Multi-objective feature selection by using NSGA-II for customer churn prediction in telecommunicationsExpert Systems with Applications, 2010
- Model of Customer Churn Prediction on Support Vector MachineSystems Engineering - Theory & Practice, 2008
- Toward a hybrid data mining model for customer retentionKnowledge-Based Systems, 2007
- Applying data mining to telecom churn managementExpert Systems with Applications, 2006
- Clustering multivariate time‐series dataJournal of Chemometrics, 2005
- Mixed Methods Research: A Research Paradigm Whose Time Has ComeEducational Researcher, 2004
- Customer attrition analysis for financial services using proportional hazard modelsEuropean Journal of Operational Research, 2004
- A novel evolutionary data mining algorithm with applications to churn predictionIEEE Transactions on Evolutionary Computation, 2003
- Turning telecommunications call details to churn prediction: a data mining approachExpert Systems with Applications, 2002
- Analysis of a complex of statistical variables into principal components.Journal of Educational Psychology, 1933