A Computational Intelligence based Approach to Telecom Customer Classification for Value Added Services

  • Abhay Bhadani
  • Ravi Shankar
  • D. Vijay Rao
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 201)


Customer classification is an imperative task for any organization catering to different market segments. In telecom industry it becomes even more important to identify which value added services (VAS) would be successful with a given customer segment. VAS provide a flexible revenue model that can be customized to different customer segments based on several attributes such as usage and preferences. Selecting and customizing VAS provides a wide canvas to the operators for maximizing their returns on the customer portfolio. Computational intelligence techniques such as Artificial Neural Network (ANN) and Support Vector Machine (SVM) have been successfully used for data mining and machine learning. These techniques provide a mathematical framework for identifying customers profiles and patterns in large datasets that representing the customers’ data and their preferences. In this paper, we propose a methodology using SVM and ANN techniques to classify telecom customer data and identify the VAS best suited for the customer segment. We test our results with the SVM yielding high prediction accuracy for the unknown public test data with Radial Basis Function (RBF) Kernel using grid search technique.


Customer data classification Support vector machine Artificial neural network Value added services 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Ahn, H., Ahn, J. J., Byun, H. W.,& Oh, K. J. (2011, September). A novel cus- tomer scoring model to encourage the use of mobile value added services. Expert Syst. Appl., 38 (9), 11693–11700.Google Scholar
  2. Ahn, H., Ahn, J. J., Oh, K. J.,& Kim, D. H. (2011, May). Facilitating cross-selling in a mobile telecom market to develop customer classification model based on hybrid data mining techniques. Expert Syst. Appl., 38 (5), 5005–5012.Google Scholar
  3. Ahn, H., Song, C., Ahn, J. J., Lee, H. Y., Kim, T. Y.,& Oh, K. J. (2010, jan.). Using hybrid data mining techniques for facilitating cross-selling of a mobile telecom market to develop customer classification model. In System sciences (hicss), 2010 43rd hawaii international conference on (p. 1–10).Google Scholar
  4. Chang, C. C.,& Lin, C. (2001). Libsvm: A library for support vector machines. Available from cjlin/libsvm
  5. Constantiou, I. D. (2009, August). Consumer behaviour in the mobile telecom- munications’ market: The individual’s adoption decision of innovative ser- vices. Telemat. Inf., 26 (3), 270–281.Google Scholar
  6. Cui, D.,& Curry, D. (2005, October). Prediction in marketing using the support vector machine. Marketing Science, 24, 595–615.Google Scholar
  7. Guo-en, X.,& Wei-dong, J. (2008). Model of customer churn prediction on support vector machine. Systems Engineering - Theory&amp. Practice, 28 (1), 71–77.Google Scholar
  8. Hsu, C.-w., Chang, C.-c.,& Lin, C.-j. (2010). A practical guide to support vector classification. Bioinformatics, 1 (1), 1–16.Google Scholar
  9. Huang, B., Kechadi, M. T.,& Buckley, B. (2012, January). Customer churn prediction in telecommunications. Expert Syst. Appl., 39 (1), 1414–1425.Google Scholar
  10. Huang, J.-J., Tzeng, G.-H.,& Ong, C.-S. (2007). Marketing segmentation using support vector clustering. Expert Syst. Appl., 32 (2), 313–317.Google Scholar
  11. Ishaya, T.,& Folarin, M. (2012, August). A service oriented approach to business intelligence in telecoms industry. Telemat. Inf., 29 (3), 273–285.Google Scholar
  12. Lee, Y.-C. (2007). Application of support vector machines to corporate credit rating prediction. Expert Systems with Applications, 33 (1), 67–74.Google Scholar
  13. Lovell, B. C.,& Walder, C. J. (2006). Business applications and computational intelligence. In K. Voges& N. Pope (Eds.), (pp. 267–290). Hershey, PA., U.S.A.: Idea Group.Google Scholar
  14. Mazzoni, C., Castaldi, L.,& Addeo, F. (2007, November). Consumer behavior in the italian mobile telecommunication market. Telecommun. Policy, 31 (10–11), 632–647.Google Scholar
  15. Pendharkar, P. C. (2009, April). Genetic algorithm based neural network ap- proaches for predicting churn in cellular wireless network services. Expert Syst. Appl., 36 (3), 6714–6720.Google Scholar
  16. Politz, A.,& Deming, W. E. (1953). On the necessity to present consumer preferences as predictions. Journal of Marketing, 18 (1), pp. 1–5.Google Scholar
  17. Reuver, M. de,& Haaker, T. (2009, August). Designing viable business models for context-aware mobile services. Telemat. Inf., 26 (3), 240–248.Google Scholar
  18. Rosenblatt, F. (1962). Principal of neurodynamics. Spartan Books.Google Scholar
  19. Sapankevych, N.,& Sankar, R. (2009, may). Time series prediction using support vector machines: A survey. Computational Intelligence Magazine, IEEE, 4 (2), 24–38.Google Scholar
  20. Sharma, A.,& Panigrahi, D. P. K. (2011, August). A neural network based approach for predicting customer churn in cellular network services. In- ternational Journal of Computer Applications, 27 (11), 26–31.Google Scholar
  21. Souza, C. R. (2010, 17 March). Kernel functions for machine learning applications. Available from kernel-functions-for-machine-learning.html
  22. Vapnik, V. N. (1995). The nature of statistical learning theory. New York, NY, USA: Springer-Verlag New York, Inc.Google Scholar
  23. Vapnik, V. N. (1998). Statistical learning theory. New York: Wiley.Google Scholar
  24. Venugopal, V.,& Baets, W. (1994). Neural networks and statistical techniques in marketing research: A conceptual comparison. Marketing Intelligence Planning, 12 (7), 30–38.Google Scholar
  25. Wang, C.,& Wang, Y.-Q. (2009, june). Segmentation of consumer’s purchase behavior based on neural network. In Cognitive informatics, 2009. icci ’09. 8th ieee international conference on (p. 552–556).Google Scholar
  26. Weiss, G. M. (2005). Data mining in telecommunications. In The data mining and knowledge discovery handbook (p. 1189–1201).Google Scholar
  27. Wu, T.-K., Huang, S.-C.,& Meng, Y.-R. (2008). Evaluation of ann and svm classifiers as predictors to the diagnosis of students with learning disabil- ities. Expert Systems with Applications, 34 (3), 1846–1856.Google Scholar
  28. Yeh, C.-C., Chi, D.-J.,& Hsu, M.-F. (2010). A hybrid approach of dea, rough set and support vector machines for business failure prediction. Expert Systems with Applications, 37 (2), 1535–1541.Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  1. 1.Bharti School of Telecommunication Technology and ManagementIndian Institute of Technology DelhiDelhiIndia
  2. 2.Department of Management StudiesIndian Institute of Technology DelhiDelhiIndia
  3. 3.Institute for Systems Studies and AnalysesDefence Research and Development Organization (DRDO)DelhiIndia

Personalised recommendations