Short Communication: Churn models for prepaid customers in the cellular telecommunication industry using large data marts

Authors:
Marcin Owczarczuk
Affiliations:
Institute of Econometrics, Warsaw School of Economics Al. Niepodleglosci 164, 02-554 Warsaw, Poland
Venue:
Expert Systems with Applications: An International Journal
Year:
2010

Citing 2
Cited 7

Review: Application of data mining techniques in customer relationship management: A literature review and classification

Expert Systems with Applications: An International Journal
Genetic algorithm based neural network approaches for predicting churn in cellular wireless network services

Expert Systems with Applications: An International Journal

Analytical customer relationship management in insurance industry using data mining: a case study of Indian insurance company

International Journal of Networking and Virtual Organisations
Insolvency modeling in the cellular telecommunication industry

Expert Systems with Applications: An International Journal
Modeling partial customer churn: On the value of first product-category purchase sequences

Expert Systems with Applications: An International Journal
Implications of mandatory registration of mobile phone users in Africa

Telecommunications Policy
Determination of Algorithms Making Balance Between Accuracy and Comprehensibility in Churn Prediction Setting

International Journal of Information Retrieval Research
Mobile phone customer retention strategies and Chinese e-commerce

Electronic Commerce Research and Applications
Intelligent churn prediction in telecom: employing mRMR feature selection and RotBoost based ensemble classification

Applied Intelligence

Quantified Score

Hi-index	12.06

Visualization

Abstract

In this article, we test the usefulness of the popular data mining models to predict churn of the clients of the Polish cellular telecommunication company. When comparing to previous studies on this topic, our research is novel in the following areas: (1) we deal with prepaid clients (previous studies dealt with postpaid clients) who are far more likely to churn, are less stable and much less is known about them (no application, demographical or personal data), (2) we have 1381 potential variables derived from the clients' usage (previous studies dealt with data with at least tens of variables) and (3) we test the stability of models across time for all the percentiles of the lift curve - our test sample is collected six months after the estimation of the model. The main finding from our research is that linear models, especially logistic regression, are a very good choice when modelling churn of the prepaid clients. Decision trees are unstable in high percentiles of the lift curve, and we do not recommend their usage.