Application of Social Network Inferred Data to Churn Modeling in Telecoms

• Autorzy: Gruszczyński W. , Arabas P.
• Języki publikacji: EN

Abstrakty

EN

The subject of this work is the use of social network analysis to increase the effectiveness of methods used to predict churn of telephony network subscribers. The social network is created on the basis of operational data (CDR records). The result of the analysis is customer segmentation and additional predictor variables. Proposed hybrid predictor employs set of regression models tuned to specific customer segments. The verification was performed on data obtained from one of the Polish operators.

Słowa kluczowe

EN

churn reduction; classification; social networks

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2016
• Tom: nr 2
• Strony: 77--86
• Opis fizyczny: Bibliogr. 22 poz., rys., tab.

Twórcy

autor

Gruszczyński W.

• Codeflip, Belgradzka st 4/40, 02-793 Warsaw

autor

Arabas P.

• Researchand Academic Computer Network (NASK), Wąwozowa st 18, 02-796 Warsaw, Poland
• Institute of Control and Computation Engineering, Warsaw University of Technology, Nowowiejska st 15/19, 00-665 Warsaw, Poland

Bibliografia

• [1] H. Kim and C. Yoon, “Determinants of subscriber churn and customer loyalty in the Korean mobile telephony market”, Telecommun. Policy, vol. 28, no. 9–10, pp. 751–765, 2004.
• [2] C. Borna, “Combating customer churn”, Telecommun. – Americas Edit., vol. 34, no. 3, pp. 83–85, 2000.
• [3] G. M. Weiss, “Data mining in telecommunications”, in Data Mining and Knowledge Discovery Handbook. Kluwer Academic, 2005.
• [4] W. Gruszczyński and P. Arabas, “Application of social network to improve effectiveness of classifiers in churn modelling”, in Proc. Int. Conf. Computat. Aspects of Soc. Netw. CASoN 2011, Salamanca, Spain, 2011, pp. 217–222.
• [5] T. Mutanen, “Customer churn analysis – a case study”, VTT Research Report no. VTT-R-01184-06, 2006 [Online]. Available: http://www.vtt.fi/inf/julkaisut/ muut/2006/customer churn case study.pdf
• [6] V. Yeshwanth, V. Vimal Raj, and M. Saravanam, “Evolutionary churn prediction in mobile networks using hybrid learning”, in Proc. 24th Florida Artif. Intell. Res. Soc. Conf. FLAIRS-24, Palm Beach, FL, USA, 2011, pp. 471–476.
• [7] T. Sato, B. Q. Huang, Y. Huang, and M. T. Kechadi, “Local PCA regression for missing data estimation in telecommunication dataset”, in 11th Pacific Rim Int. Conf. Artif. Intell. PRICAI 2010, Daegu, Korea, 2010, pp. 668–673.
• [8] J. Haden, A. Tiwari, R. Roy, and D. Ruta, “Churn prediction using complaints data”, in Proc. World Academy of Science, Engineering and Technology, vol. 19, 2006.
• [9] A. L. Barabasi and R. Albert, “Emergence of scaling in random networks”, Science, vol. 286, no. 5439, pp. 509–512, 1999.
• [10] M. E. J. Newman and M. Girvan, “Finding and evaluating community structure in networks”, Physical Review E, 69, 026113, 2002.
• [11] Y. Richter, E. Yom-Tov, and N. Slonim, “Predicting customer churn in mobile networks through analysis of social groups”, in Proc. SIAM Int. Conf. on Data Mining SDM 2010, Columbus, OH, USA, 2010, pp. 732–741.
• [12] K. Dasgupta, R. Singh, and B. Viswanathan, “Social ties and their relevance to churn in mobile database technoltelecom networks”, in Proc. 11th Int. Conf. on Extending Database Technology: Ad- vances in Database Technology EDBT’08, Nantes, France, 2008, pp. 668–677.
• [13] M. Karnstedt, M. Rowe, J. Chan, H. Alani, and C. Hayes, “The effect of user features on churn in social networks”, in Proc. 3rd Int. Web Science Conf. WebSci’11, Koblenz, Germany, 2011, pp. 1–8.
• [14] M. Zawisza, P. Wojewnik, B. Kamiński, and M. Antosiewicz, “Social-network influence on telecommunication customer attrition”, in Agent and Multi-Agent Systems: Technologies and Applications LNCS, vol. 6682, pp. 64–73. Springer, 2011.
• [15] M. N. Abd-Allah, A. Salah, and S. R. El-Beltagy, “Enhanced customer churn prediction using social network analysis”, in Proc. 3rd Worksh. Data-Driven User Behav. Model. & Mining from Social Media DUBMOD’14, Shanghai, China, 2014, pp. 11–12.
• [16] W. Verbeke, D. Martens, and B. Baesens, “Social network analysis for customer churn prediction”, Appl. Soft Comput., vol. 14, pp. 431–446, 2014.
• [17] M. Kamola, E. Niewiadomska-Szynkiewicz, and B. Piech, “Reconstruction of a social network graph from incomplete call detail records”, in Proc. Int. Conf. Computat. Aspects of Soc. Netw. CASoN 2011, Salamanca, Spain, 2011, pp. 136–140.
• [18] W. Aiello, F. Chung, and L. Lu, “A random graph model for massive graphs”, Proc. 32nd Annual ACM Symp. Theory of Comput. STOC ’00, Portland, OR, USA, 2000, pp. 171–180.
• [19] LaNet-vi website [Online]. Available: http://lanet-vi.fi.uba.ar/
• [20] Igraph: Network Analysis and Visualisation [Online]. Available: http://cran.r-project.org/web/packages/igraph/
• [21] D. M. W. Powers, “Evaluation: From precision, recall and F-measure to ROC, informedness, markedness & correlation”, J. Machine Learn. Technol., vol. 2, no. 1, 37–63, 2011.
• [22] R. Kasprzyk and Z. Tarapata, “Graph-based optimization method for information diffusion and attack durability in networks”, in Rough Sets and Current Trends in Computing, M. Szczuka, M. Kryszkiewicz, S. Ramanna, R. Jensen, and Q. Hu, Eds., LNCS, vol. 6086, pp. 698–709. Springer, 2010.