{"references": ["Van Den Poel, D. and B. Lariviere, Customer attrition analysis for\nfinancial services using proportional hazard models. European journal of\noperational research, 2003. 157: p. 196-217.", "Wei, C. and I. Chiu, Turning telecommunications call details to churn\nprediction: a data mining approach. Expert systems with applications,\n2002. 23: p. 103-112.", "Kim, H. and C. Yoon, Determinants of Subscriber Churn and Customer\nLoyalty in the Korean Mobile Telephony Market. Telecommunications\nPolicy, 2004. 28: p. 751-765.", "Liu, D. and Y. Shih, Integrating AHP and Data mining for Product\nRecommendation Based on Customer Lifetime Value. Information &\nManagement, 2004. 42(3): p. 387-400.", "Canning, G., Do A Value Analysis of Your Customer Base. Industrial\nMarketing Management, 1982. 11: p. 89-93.", "Chan, P.K., et al., Distributed data mining in credit card fraud detection.\nIntelligent Systems and Their Applications, IEEE, 1999. 14(6): p. 67-74.", "Au, W., C.C. Chan, and X. Yao, A novel evolutionary data mining\nalgorithm with applications to churn prediction. IEEE transactions on\nevolutionary computation, 2003. 7(6): p. 532-545.", "Hsieh, N., An Integrated Data Mining and Behavioural Scoring Model\nfor Analysing Bank Customers. Expert systems with applications, 2004.\n27: p. 623-633.", "Hwang, H. and T. Euiiho Suh, An LTV Model and Customer\nSegmentation Based on Customer Value: A Case Study on the Wireless\nTelecommunications Industry. Expert systems with applications, 2004.\n26: p. 181-188.\n[10] Datta, P., et al., Automated cellular modeling and prediction on a large\nscale. Issues on the application of data mining, 2001(14): p. 485-502.\n[11] Rosset, S., et al. Customer Lifetime Value Modelind and its Use for\nCustomer Retention Planning. in Proceedings of the ACM SIGKDD\nInternational Conference on Knowledge Discovery and Data Mining.\n2002. Canada: Association for Computing Machinery.\n[12] Rygielski, C., J. Wang, and D.C. Yen, Data Mining Techniques for\nCustomer Relationship Management. Technology in Society, 2002. 24:\np. 483-502.\n[13] Boone, D.S. and M. Roehm, Retail Segmentation Using Artificial Neural\nNetworks. International journal of research in marketing, 2002. 19: p.\n287-301.\n[14] Vellido, A., P.J.G. Lisboa, and K. Meehan, Segmentation of the Online\nShopping Market Using Neural Networks. Expert systems with\napplications, 1999. 17: p. 303-314.\n[15] Kavzoglu, T. and P.M. Mather, The role of feature selection in artificial\nneural network applications. International Journal of Remote Sensing,\n2001. 23(15): p. 2919-2937.\n[16] Meyer-Base, A. and R. Watzel, Transformational Radial Basis Neural\nNetwork for Relevant Feature Selection. Pattern Recognition, 1998. 19:\np. 1301-1306.\n[17] Dudoit, S. and M.J. Van Der Laan, Asymptotics of cross-validated risk\nestimation in estimator selection and performance assessment. Statistical\nMethodology, 2003. 2: p. 131-154.\n[18] Baesens, B., et al., Bayesian Network Classifiers for Identifying the\nSlope of the Customer Lifecycle of Long-Life Customers. European\nJornal of operational Research, 2004. 156: p. 508-523.\n[19] Bloemer, J., et al., Comparing complete and partial classification for\nidentifying customers at risk. International journal of research in\nmarketing, 2002. 20: p. 117-131.\n[20] Lee, H., Semantics of recursive relationships in entity-relationship\nmodel. Information and software technology, 1999. 41: p. 877-886.\n[21] Fong, J. and S.K. Cheung, Translating relational schema into XML\nschema definition with data semantic preservation and XSD graph.\nInformation and software technology, 2004. 47: p. 437-462.\n[22] Ho Ha, S., S. Min Bae, and S. Chan Park, Customer's Time-Variant\nPurchase Behavior and Corresponding Marketing Strategies: An Online\nRetailer's Case. Computers and Industrial Engineering, 2002. 43: p. 801-\n820.\n[23] Shin, H.W. and S.Y. Sohn, Segmentation of Stock Trading Customers\nAccording to Potential Value. Expert systems with applications, 2004.\n27: p. 27-33.\n[24] Behara, R.S., W.W. Fisher, and J. Lemmink, Modelling and evaluating\nservice quality measurement using neural networks. International journal\nof operations and production management, 2002. 22(10): p. 1162-1185.\n[25] Liao, Y., S. Fang, and H. Nuttle, S, A neural network model with bound\nweights and for pattern classification. Computers and Operational\nResearch, 2004. 31: p. 1411-1426.\n[26] Muata, K. and O. Bryson, Evaluation of decision trees: a multi criteria\napproach. Computers and Operational Research, 2004. 31: p. 1933-1945.\n[27] Mihelis, G., et al., Customer Satisfaction Measurement in the Private\nBank Sector. European Jornal of operational Research, 2001. 130: p.\n347-360.\n[28] Rust, R.T. and A.J. Zahorik, Customer Satisfaction, Customer Retention,\nand Market Share. Journal of retailing, 1993. 69(2): p. 193-215."]}

The aim of this paper is to identify the most suitable model for churn prediction based on three different techniques. The paper identifies the variables that affect churn in reverence of customer complaints data and provides a comparative analysis of neural networks, regression trees and regression in their capabilities of predicting customer churn.