The effect of social affinity and predictive horizon on churn prediction using diffusion modeling

Original Article

Abstract

The social influence of people on their peers in the selection of products and services is frequently modeled as a diffusion process. Recently, such processes have been successfully applied as a tool for predicting customer turnover, or churn, in mobile communication carriers. These predictions are most accurate when specific social ties are used in the diffusion process, and are primarily useful when they provide a long forecast horizon, so as to enable a service provider to take mitigating actions. Here, we investigate several measures of social affinity and compare their performances for churn prediction, using data from two large mobile phone carriers. Our analysis demonstrates that the various measures of social ties capture different calling and texting patterns, and that a significant improvement in the accuracy of prediction is reached by combining them. We study the predictive horizon of diffusion processes and show that it deteriorates significantly as the horizon increases. Our findings underline the usefulness of diffusion processes for enhancing churn prediction while providing insights to their limitations.

Keywords

Churn prediction Diffusion processes Telco Social networks 

References

  1. Adamic LA, Adar E (2001) Friends and neighbors on the web. Soc Netw 25:211–230CrossRefGoogle Scholar
  2. Birke D (2006) Diffusion on networks: modelling the spread of innovations and customer churn over social networks. Workshop on Formation of Social Networks in Social Software ApplicationsGoogle Scholar
  3. Coussement K, Van den Poel D (2008) Churn prediction in subscription services: an application of support vector machines while comparing two parameter-selection techniques. Expert Syst Appl 34(1):313–327CrossRefGoogle Scholar
  4. Crandall D, Cosley D, Huttenlocher D, Kleinberg J, Suri S (2008) Feedback effects between similarity and social influence in online communities. In: Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, pp 160–168Google Scholar
  5. Dasgupta K, Singh R, Viswanathan B, Chakraborty D, Mukherjea S, Nanavati AA, Joshi A (2008) Social ties and their relevance to churn in mobile telecom networks. In: EDBT ’08: Proceedings of the 11th international conference on extending database technologyGoogle Scholar
  6. Datta P, Masand B, Mani DR, Li B (2000) Automated cellular modeling and prediction on a large scale. Artif Intell Rev 14(6):485–502CrossRefMATHGoogle Scholar
  7. de Oliveira Lima E (2009) Domain knowledge integration in data mining for churn and customer lifetime value modelling: new approaches and applications. PhD thesis, School of Management, University of SouthamptonGoogle Scholar
  8. Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30MathSciNetMATHGoogle Scholar
  9. Dierkes T, Bichler M, Krishnan R (2011) Estimating the effect of word of mouth on churn and cross-buying in the mobile phone market with markov logic networks. Decis Support Syst 51(3):361–371CrossRefGoogle Scholar
  10. Doyle S, Barn S (2007) The role of social networks in marketing. J Database Mark Customer Strategy Manag 15(1):60–64CrossRefGoogle Scholar
  11. Gopal RK, Meher SK (2008) Customer churn time prediction in mobile telecommunication industry using ordinal regression. In: Lecture Notes in Computer Science, vol 5012, Springer, pp 884–889Google Scholar
  12. Gruhl D, Guha R, Liben-Nowell D, Tomkins A (2004) Information diffusion through blogspace. In: Proceedings of the 13th international conference on World Wide Web, ACM, WWW ’04, pp 491–501Google Scholar
  13. Hadden J, Tiwari A, Roy R, Ruta D (2007) Computer assisted customer churn management: State-of-the-art and future trends. Comput Oper Res 34(10):2902–2917CrossRefMATHGoogle Scholar
  14. Huang B, Kechadi MT, Buckley B (2012) Customer churn prediction in telecommunications. Expert Syst Appl 39(1):1414–1425CrossRefGoogle Scholar
  15. Idris A, Rizwan M, Khan A (2012) Churn prediction in telecom using random forest and pso based data balancing in combination with various feature selection strategies. Comput Electr Eng 38(6):1808–1819CrossRefGoogle Scholar
  16. Iyengar R, Van den Bulte C, Valente TW (2011) Opinion leadership and social contagion in new product diffusion. Mark Sci 30(2):195–212CrossRefGoogle Scholar
  17. Jadhav RJ, Pawar UT (2011) Churn prediction in telecommunication using data mining technology. Int J Adv Comput Sci Appl 2(2):17–19Google Scholar
  18. Karnstedt M, Hennessy T, Chan J, Hayes C (2010) Churn in social networks: a discussion boards case study. In: IEEE Second international conference on social computing (SocialCom), 2010, pp 233–240Google Scholar
  19. Kawale J, Pal A, Srivastava J (2009) Churn prediction in mmorpgs: a social influence based approach. In: IEEE international conference on computational science and engineering, vol 4, pp 423–428Google Scholar
  20. Kempe D, Kleinberg J, Tardos E (2003) Maximizing the spread of influence through a social network. In: Proceedings of the ninth ACM SIGKDD international conference on knowledge discovery and data mining, KDD ’03Google Scholar
  21. Kossinets G, Watts DJ (2009) Origins of homophily in an evolving social network1. Am J Sociol 115(2):405–450CrossRefGoogle Scholar
  22. Lu N, Lin H, Lu J, Zhang G (2012) A customer churn prediction model in telecom industry using boosting. Industrial Informatics, IEEE Transactions on PP(99):1–1.Google Scholar
  23. Ma H, Yang H, Lyu MR, King I (2008) Mining social networks using heat diffusion processes for marketing candidates selection. In: Proceedings of the 17th ACM conference on information and knowledge management, ACM, New York, NY, USA, CIKM 2008, pp 233–242Google Scholar
  24. Neslin SA, Gupta S, Kamakura W, Lu J, Mason CH (2006) Defection detection: measuring and understanding the predictive accuracy of customer churn models. J Mark Res 43(2):204–211CrossRefGoogle Scholar
  25. Nitzan I, Libai B (2010) Social effects on customer retention. Marketing Science Institute (MSI) Working PaperGoogle Scholar
  26. Pendharkar PC (2009) Genetic algorithm based neural network approaches for predicting churn in cellular wireless network services. Expert Syst Appl 36(3):6714–6720CrossRefGoogle Scholar
  27. Peres R, Mahajan V, Eitan M (2010) Innovation diffusion and new product growth: a critical review and research directions. Int J Res Mark 1:91–106CrossRefGoogle Scholar
  28. Richter Y, Yom-Tov E, Slonim N (2010) Predicting customer churn in mobile networks through analysis of social groups. In: SDM, pp 732–741Google Scholar
  29. Sarkar P, Chakrabarti D, Moore A (2010) Theoretical justification of popular link prediction heuristics. In: 23st annual conference on learning theory, COLT 2010Google Scholar
  30. Song G, Yang D, Wu L, Wang T, Tang S (2006) A mixed process neural network and its application to churn prediction in mobile communications. In: Proceedings of the sixth IEEE international conference on data mining workshops (ICDM Workshops), pp 798–802Google Scholar
  31. Spearman C (1904) The proof and measurement of association between two things. Am J Psychol 15(2):72–101CrossRefGoogle Scholar
  32. Toledano H, Yom-Tov E, Pelleg D, Pednault E, Natarajan R (2008) Support vector machine solvers: large-scale, accurate, and fast (pick any two). Tech Rep H-0260, IBM ResearchGoogle Scholar
  33. Wang Y, Cong G, Song G, Xie K (2010) Community-based greedy algorithm for mining top-k influential nodes in mobile social networks. In: Proceedings of the 16th ACM SIGKDD international conference on knowledge discovery and data mining, ACM, New York, NY, USA, KDD 2010, pp 1039–1048Google Scholar
  34. Yang J, He X, Lee H (2007) Social reference group influence on mobile phone purchasing behaviour: a cross-nation comparative study. Int J Mob Commun 5(3):319–338CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 2014

Authors and Affiliations

  1. 1.IBM Research-HaifaHaifa University CampusHaifaIsrael
  2. 2.Microsoft ResearchHerzeliyaIsrael

Personalised recommendations