Privacy preserving churn prediction

ABSTRACT

Churn prediction is an important component of customer retention to predict whether a current customer decides to take business elsewhere or voluntarily terminates service, so marketing campaigns can target at the potential churners for retention efforts. In this paper we provide a strategy to protect customers' privacy in churn prediction. First of all, we demonstrate how to use data distortion to mask a telecom customer dataset, and then apply churn prediction methods to the distorted data. Since the distorted data are so different from the original data the privacy of customer is preserved, but the prediction methods we proposed will not compromise the accuracy of churn prediction. The performance of several data distortion methods are compared and evaluated.

REFERENCES

• 1: Dakshi Agrawal , Charu C. Aggarwal, On the design and quantification of privacy preserving data mining algorithms, Proceedings of the twentieth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems, p.247-255, May 2001, Santa Barbara, California, United States [doi>10.1145/375551.375602]
• 2: Rakesh Agrawal , Ramakrishnan Srikant, Privacy-preserving data mining, Proceedings of the 2000 ACM SIGMOD international conference on Management of data, p.439-450, May 15-18, 2000, Dallas, Texas, United States
• 3: Au, W., Chan, K. C., & Yao, X. (2003). A novel evolutionary data mining algorithm with application to churn prediction. IEEE Transactions on Evolutionary Computation, 7 (6), 532--545.
• 4: Burez, J., & Poel, D. (2008). Handling class imbalance in customer churn prediction. Ghent University, Faculty of Economics and Business Administration.
• 5: Keke Chen , Ling Liu, Privacy Preserving Data Classification with Rotation Perturbation, Proceedings of the Fifth IEEE International Conference on Data Mining, p.589-592, November 27-30, 2005 [doi>10.1109/ICDM.2005.121]
• 6: Chen, K., & Liu, L. (2007). Towards attach-resilient geometric data perturbation. Proceedings of the 7th SIAM International Conference on Data Ming. Minneapolis, Minnesota.
• 7: Koustuv Dasgupta , Rahul Singh , Balaji Viswanathan , Dipanjan Chakraborty , Sougata Mukherjea , Amit A. Nanavati , Anupam Joshi, Social ties and their relevance to churn in mobile telecom networks, Proceedings of the 11th international conference on Extending database technology: Advances in database technology, March 25-29, 2008, Nantes, France [doi>10.1145/1353343.1353424]
• 8: Domingo-Ferrer, J., & Mateo-Sanz, J. M. (2001). An empirical comparison of SDC methods for continuous microdata in terms of information loss and disclosure risk. Second Eurostat-UN/ECE Joint Work Session on Statistical Data Confidentiality. Skopje, Macedonia.
• 9: Hadden, J., Tiwari, A., Roy, R., & Ruta, D. (2006). Churn prediction: Does technology matter? International Journal of Intelligent Systems and Technologies, 1 (2), 104--110.
• 10: John Hadden , Ashutosh Tiwari , Rajkumar Roy , Dymitr Ruta, Computer assisted customer churn management: State-of-the-art and future trends, Computers and Operations Research, v.34 n.10, p.2902-2917, October, 2007 [doi>10.1016/j.cor.2005.11.007]
• 11: Jamal, Z., & Bucklin, R. E. (2006). Improving the diagnosis and prediction of customer churn: A heterogeneous hazard modeling approach. JOURNAL OF INTERACTIVE MARKETING, 20 (3--4), 16--29.
• 12: Hillol Kargupta , Souptik Datta , Qi Wang , Krishnamoorthy Sivakumar, On the Privacy Preserving Properties of Random Data Perturbation Techniques, Proceedings of the Third IEEE International Conference on Data Mining, p.99, November 19-22, 2003
• 13: Mohammed Ketel , Abdollah Homaifar, Privacy-preserving mining by rotational data transformation, Proceedings of the 43rd annual Southeast regional conference, March 18-20, 2005, Kennesaw, Georgia [doi>10.1145/1167350.1167419]
• 14: Kun Liu , Hillol Kargupta , Jessica Ryan, Random Projection-Based Multiplicative Data Perturbation for Privacy Preserving Distributed Data Mining, IEEE Transactions on Knowledge and Data Engineering, v.18 n.1, p.92-106, January 2006 [doi>10.1109/TKDE.2006.14]
• 15: Klosgen, W. (1995). Anonymization techniques for knowledge discovery in databases. Proceedings of the First International Conference on Knowledge Discovery and Data Mining, (pp. 186--191). Montreal, Canada.
• 16: Lejeune, M. A. (2001). Measuring the impact of data mining on churn management. Internet Research: Electronic Networking Applications and Policy, 11 (5), 375--387.
• 17: Mozer, M., Wolneiwicz, R., Grimes, D., Johnson, E., & Kaushansky, H. (2000). Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry. IEEE Transactions on Neural Networks, 11 (3), 690--696.
• 18: Shibnath Mukherjee , Zhiyuan Chen , Aryya Gangopadhyay, A privacy-preserving technique for Euclidean distance-based mining algorithms using Fourier-related transforms, The VLDB Journal — The International Journal on Very Large Data Bases, v.15 n.4, p.293-315, November 2006 [doi>10.1007/s00778-006-0010-5]
• 19: Krishnamurty Muralidhar , Rathindra Sarathy, Security of random data perturbation methods, ACM Transactions on Database Systems (TODS), v.24 n.4, p.487-493, Dec. 1999 [doi>10.1145/331983.331986]
• 20: Neslin, S. A., Gupta, S., Kamakura, W., Lu, J., & Mason, C. H. (2006). Defection detection: Measuring and understanding the predictive accuracy of customer churn models. Journal of marketing research, 43 (2), 204--211.
• 21: Oliveira, S. R., & Zaïïane, O. R. (2004). Data Perturbation by Rotation for Privacy-Preserving Clustering. Technical Report, TR04-17, University of Alberta, Computer Science Department.
• 22: Oliveira, S. R., & Zaiane, O. R. (2003). Privacy preserving clustering by data transformation. Proc. of the 18th Brazilian Symposium on Databases (SBBD 2003), (pp. 304--318). Manaus, Brazil.
• 23: Reuters. (2002). Retrieved from http://news.com.com/2100-1033-276151.html?legacy=cnet
• 24: Latanya Sweeney, k-anonymity: a model for protecting privacy, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, v.10 n.5, p.557-570, October 2002 [doi>10.1142/S0218488502001648]
• 25: Vapnik, V. N. (1998). Statistical Learning Theory. New York: John Wiley & Sons.
• 26: Xu, S., & Lai, S. (2007). Fast Fourier Transform Based Data Perturbation Method for Privacy Protection. Proceedings of IEEE International Conference on Intelligence and Security Informatics. New Brunswick, NJ.
• 27: Shuting Xu , Jun Zhang , Dianwei Han , Jie Wang, Singular value decomposition based data distortion strategy for privacy protection, Knowledge and Information Systems, v.10 n.3, p.383-397, October 2006 [doi>10.1007/s10115-006-0001-2]

INDEX TERMS

Primary Classification:
  J. Computer Applications
  J.1 ADMINISTRATIVE DATA PROCESSING
      Subjects: Business

General Terms:
Algorithms

Keywords:
churn, data mining, prediction, privacy