User Modeling for Telecommunication Applications: Experiences and Practical Implications

  • Heath Hohwald
  • Enrique Frías-Martínez
  • Nuria Oliver
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6075)


Telecommunication applications based on user modeling focus on extracting customer behavior and preferences from the information implicitly included in Call Detail Record (CDR) datasets. Even though there are many different application areas (fraud detection, viral and targeted marketing, churn prediction, etc.) they all share a common data source (CDRs) and a common set of features for modeling the user. In this paper we present our experience with different applications areas in generating user models from massive real datasets of both mobile phone and landline subscriber activity. We present the analysis of a dataset containing the traces of 50,000 mobile phone users and 50,000 landline users from the same geographical area for a period of six months and compare the different behaviors when using landlines and mobile phones and the implications that such differences have for each application. Our results indicate that user models for a variety of applications can be generated efficiently and in a homogeneous way using an architecture based on distributed computing and that there are numerous differences between mobile phone and landline users that have relevant practical implications.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Seshadri, M., Machiraju, S., Sridharan, A., Bolot, J., Faloutsos, C., Leskovec, J.: Mobile call graphs: Beyond power-law and lognormal distributions. In: KDD ’08, pp. 596–604 (2008)Google Scholar
  2. 2.
    Dasgupta, K., Singh, R., Viswanathan, B., Chakraborty, D., Mukherjea, S., Nanavati, A.A., Joshi, A.: Social ties and their relevance to churn in mobile telecom networks. In: EDBT ’08, pp. 668–677. ACM, New York (2008)Google Scholar
  3. 3.
    Nanavati, A.A., Gurumurthy, S., Das, G., Chakraborty, D., Dasgupta, K., Mukherjea, S., Joshi, A.: On the structural properties of massive telecom call graphs: findings and implications. In: CIKM ’06: Proceedings of the 15th ACM international conference on Information and knowledge management, pp. 435–444. ACM Press, New York (2006)CrossRefGoogle Scholar
  4. 4.
    Onnela, J.P., Saramaki, J., Hyvonen, J., Szabo, G., Lazer, D., Kaski, K., Kertesz, J., Barabasi, A.L.: Structure and tie strengths in mobile communication networks. Proceedings of the National Academy of Sciences 104(18), 7332–7336 (2007)CrossRefGoogle Scholar
  5. 5.
    Cortes, C., Pregibon, D., Volinsky, C.: Communities of interest. In: Hoffmann, F., Adams, N., Fisher, D., Guimarães, G., Hand, D.J. (eds.) IDA 2001. LNCS, vol. 2189, pp. 105–114. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  6. 6.
    Abello, J., Pardalos, P., Resende, M.G.: On maximum clique problems in very large graphs. In: Abello, J.M., Vitter, J.S. (eds.) Extrernal Memory Alogrithms. Dimacs Series In Discrete Mathematics and Theoretical Computer Science, vol. 50, pp. 119–130. American Mathematical society, Boston (1999)Google Scholar
  7. 7.
    Qi, J., Zhang, Y., Shu, H., Li, Y., Ge, L.: Churn prediction with limited information in fixed-line telecommunication. In: Proc. 5th Int. Symp. Communication Systems Networks and Digital Signal Processing, pp. 423–426 (2006)Google Scholar
  8. 8.
    Ferreira, J., Vellasco, M., Pacheco, M., Barbosa, C.: Data mining techniques on the evaluation of wireless churn. In: ESANN 2004 European Symposium on Artificial Neural Networks, Citeseer, pp. 483–488 (2004)Google Scholar
  9. 9.
    Archaux, C., Laanaya, H., Martin, A., Khenchaf, A.: An SVM based churn detector in prepaid mobile telephony. In: Int. Conf. Information & Communication Technologies (ICTTA), pp. 19–23 (2004)Google Scholar
  10. 10.
    Wei, C., Chiu, I.: Turning telecommunications call details to churn prediction. In: Expert Systems with Applications, vol. 23, pp. 4103–4112 (2002)Google Scholar
  11. 11.
    Au, W., Chan, K., Yao, X.: A novel evolutionary data mining algorithm with applications to churn prediction. IEEE Trans. Evol. Comp. 7(6), 532–545 (2003)CrossRefGoogle Scholar
  12. 12.
    Bin, L., Peiji, S., Juan, L.: Customer Churn Prediction Based on the Decision Tree in Personal Handyphone System Service. In: 2007 Int. Conf. Service Systems and Service Management, pp. 1–5 (2007)Google Scholar
  13. 13.
    Goldenberg, J., Libai, B.: Talk of the network: A complex systems look at the underlying process of word-of-mouth. Marketing Letters 12(3), 211–223 (2001)CrossRefGoogle Scholar
  14. 14.
    Richardson, M., Domingos, P.: Mining knowledge-sharing sites for viral marketing. In: Proc. 8th ACM SIGKDD, p. 70. ACM, New York (2002)Google Scholar
  15. 15.
    Ziegler, C., Lausen, G.: Spreading activation models for trust propagation. In: Proc. IEEE Int. Conf. on e-Technology, e-Commerce, and e-Service, Citeseer, pp. 83–97 (2004)Google Scholar
  16. 16.
    Estévez, P.A., Held, C.M., Perez, C.A.: Subscription fraud prevention in telecommunications using fuzzy rules and neural networks. Expert Systems with Applications 31(2), 337–344 (2006)CrossRefGoogle Scholar
  17. 17.
    Xing, D., Girolami, M.: Employing Latent Dirichlet Allocation for fraud detection in telecommunications. Pattern Recognition Letters 28(13), 1727–1734 (2007)CrossRefGoogle Scholar
  18. 18.
    Hilas, C., Sahalos, J.: User profiling for fraud detection in telecommunication networks. In: 5th Int. Conf. technology and automation, pp. 382–387 (2005)Google Scholar
  19. 19.
    Zang, H., Bolot, J.C.: Mining call and mobility data to improve paging efficiency in cellular networks. In: MobiCom ’07, pp. 123–134. ACM, New York (2007)CrossRefGoogle Scholar
  20. 20.
    How to generate customer loyalty in mobile markets. Technical report, Nokia Siemens Networks (March 2009)Google Scholar
  21. 21.
    Hohwald, H., Frias-Martinez, E., Oliver, N.: ARBUD: A Reusable Architecture for Building User Models from Massive Datasets. In: UMAP 2010 (submitted, 2010)Google Scholar
  22. 22.
    Dean, J., Ghemawat, S.: Mapreduce: Simplified data processing on large clusters, 137–150 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Heath Hohwald
    • 1
  • Enrique Frías-Martínez
    • 1
  • Nuria Oliver
    • 1
  1. 1.Data Mining and User Modeling Group, Telefonica ResearchMadridSpain

Personalised recommendations