MCS: Multiple classifier system to predict the churners in the telecom industry

Multiple classifiers for prediction or classification has gained popularity in recent years. Ensemble Technique perform best predictions as compared to traditional classifiers. This has resulted in the experimentation with new ways of ensemble creation. This paper presents a multiple classifier system (MCS) that can outperform traditional classifiers. Experiments are performed on a benchmark Customer Churn Dataset (available on UCI repository) and a newly created dataset from a South Asian wireless telecom operator. MCS achieved accuracies of 97% and 86% on the UCI churn dataset and private dataset, respectively. MCS as compared to existing best approaches realized the best results on the private and public datasets.

[1]  João Bártolo Gomes,et al.  Predicting Near-Future Churners and Win-Backs in the Telecommunications Industry , 2012, ArXiv.

[2]  Yong Liu,et al.  Research Model of Churn Prediction Based on Customer Segmentation and Misclassification Cost in the Context of Big Data , 2015 .

[3]  Rajkumar Roy,et al.  Churn Prediction: Does Technology Matter? , 2008 .

[4]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[5]  Stefan Lessmann,et al.  Maximize What Matters: Predicting Customer Churn With Decision-Centric Ensemble Selection , 2015, ECIS.

[6]  Hossam Faris,et al.  Negative Correlation Learning for Customer Churn Prediction: A Comparison Study , 2015, TheScientificWorldJournal.

[7]  Chih-Fong Tsai,et al.  Variable selection by association rules for customer churn prediction of multimedia on demand , 2010, Expert Syst. Appl..

[8]  Prabin Kumar Panigrahi,et al.  A Neural Network based Approach for Predicting Customer Churn in Cellular Network Services , 2011, ArXiv.

[9]  Guo-en Xia,et al.  Model of Customer Churn Prediction on Support Vector Machine , 2008 .

[10]  Sven Gotovac,et al.  Modeling Data Mining Applications for Prediction of Prepaid Churn in Telecommunication Services , 2010 .

[11]  Jon Atli Benediktsson,et al.  Multiple Classifier Systems , 2015, Lecture Notes in Computer Science.

[12]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[13]  Konstantinos I. Diamantaras,et al.  A comparison of machine learning techniques for customer churn prediction , 2015, Simul. Model. Pract. Theory.

[14]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[15]  David C. Yen,et al.  Applying data mining to telecom churn management , 2006, Expert Syst. Appl..

[16]  Gavril TODEREAN,et al.  PREDICTING CHURN IN MOBILE TELECOMMUNICATIONS INDUSTRY , 2013 .

[17]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[18]  Moni Naor,et al.  Multiple Classifier Systems , 2013, Lecture Notes in Computer Science.

[19]  Shuqin Cai,et al.  A Hybrid Churn Prediction Model in Mobile Telecommunication Industry , 2014 .

[20]  Bart Baesens,et al.  New insights into churn prediction in the telecommunication sector: A profit driven data mining approach , 2012, Eur. J. Oper. Res..

[21]  Yoav Freund,et al.  A Short Introduction to Boosting , 1999 .

[22]  Noel E. Sharkey,et al.  The "Test and Select" Approach to Ensemble Combination , 2000, Multiple Classifier Systems.

[23]  Shouyang Wang,et al.  Feature-selection-based dynamic transfer ensemble model for customer churn prediction , 2013, Knowledge and Information Systems.