Journal of the Operational Research Society

, Volume 67, Issue 9, pp 1135–1145 | Cite as

Predicting time-to-churn of prepaid mobile telephone customers using social network analysis

  • Aimée BackielEmail author
  • Bart Baesens
  • Gerda Claeskens
General Paper


Mobile phone carriers in a saturated market must focus on customer retention to maintain profitability. This study investigates the incorporation of social network information into churn prediction models to improve accuracy, timeliness, and profitability. Traditional models are built using customer attributes, however these data are often incomplete for prepaid customers. Alternatively, call record graphs that are current and complete for all customers can be analysed. A procedure was developed to build the call graph and extract relevant features from it to be used in classification models. The scalability and applicability of this technique are demonstrated on a telecommunications data set containing 1.4 million customers and over 30 million calls each month. The models are evaluated based on ROC plots, lift curves, and expected profitability. The results show how using network features can improve performance over local features while retaining high interpretability and usability.


decision support systems telecommunications churn prediction social network analysis survival analysis 



This research was made possible with support of the Odysseus program (Grant B.0915.09) and Grant G.0816.12N of the Fund for Scientific Research Flanders (FWO).


  1. Abbasimehr H, Setak M and Soroor J (2013). A framework for identification of high-value customers by including social network based variables for churn prediction using neuro-fuzzy techniques. International Journal of Production Research 51(4): 1279–1294.CrossRefGoogle Scholar
  2. Aksoy L, Buoye A, Aksoy P, Lariviere B and Keningham T (2013). A cross-national investigation of the satisfaction and loyalty linkage for mobile telecommunications services across eight countries. Journal of Interactive Marketing 27(1): 74–82.CrossRefGoogle Scholar
  3. Allison PD (2010). Survival Analysis Using SAS: A Practical Guide. 2nd edn, SAS Institute Inc.: Cary, NC.Google Scholar
  4. Baesens B, Van Gestel T, Stepanova M, Van den Poel D and Vanthienen J (2005). Neural network survival analysis for personal loan data. Journal of Operational Research Society 56(9): 1089–1098.CrossRefGoogle Scholar
  5. Bamber D (1975). The area above the ordinal dominance graph and the area below the receiver operating characteristic graph. Journal of Mathematical Psychology 12(4): 387–415.CrossRefGoogle Scholar
  6. Banasik J, Crook JN and Thomas LC (1999). Not if but when will borrowers default. Journal of Operational Research Society 50(12): 1185–1190.CrossRefGoogle Scholar
  7. Benoit D and den Poel D Van (2012). Improving customer retention in financial services using kinship network information. Expert Systems with Applications 39(13): 11435–11442.CrossRefGoogle Scholar
  8. Bersen A, Smith S and Thearling K (2000). Building Data Mining Applications for CRM. McGraw-Hill: New York.Google Scholar
  9. Breslow NE (1972). Contribution to the discussion on the paper by DR Cox, regression and life tables. Journal of the Royal Statistical Society 34(2): 216–217.Google Scholar
  10. Chen Z-Y, Fan Z-P and Sun M (2012). A hierarchical multiple kernel support vector machine for customer churn prediction using longitudinal behavioral data. European Journal of Operational Research 223(2): 461–472.CrossRefGoogle Scholar
  11. Chiu C, Ku Y, Lie T and Chen Y (2011). Internet auction fraud detection using social network analysis and classification tree approaches. International Journal of Electronic Commerce 15(3): 123–147.CrossRefGoogle Scholar
  12. Cox DR (1972). Regression models and life-tables. Journal of the Royal Statistical Society 34(2): 187–220.Google Scholar
  13. Cox DR (1975). Partial likelihood. Biometrika 62(2): 269–276.CrossRefGoogle Scholar
  14. Dasgupta K et al (2008). Social ties and their relevance to churn in mobile telecom networks. In: EDBT08 Proceedings of the 11th International Conference on Extending Database Technology: Advances in Database Technology, pp 668–677, Nantes, France, March. ACM.Google Scholar
  15. de Bock KW and den Poel D Van (2011). An empirical evaluation of rotation-based ensemble classifiers for customer churn prediction. Expert Systems with Applications 38(10): 12293–12301.CrossRefGoogle Scholar
  16. DeLong E, DeLong D and Clarke-Pearson D (1988). Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. International Biometric Society 44(3): 837–845.CrossRefGoogle Scholar
  17. Easley D and Kleinberg J (2010). Networks, Crowds, and Markets. Cambridge University Press: Cambridge.CrossRefGoogle Scholar
  18. Hancock PG and Raeside R (2009). Analysing communication in a complex service process: An application of social network analysis in the scottish prison service. Journal of Operational Research Society 61(2): 265–274.CrossRefGoogle Scholar
  19. Huang B, Kechadi MT and Buckley B (2012). Customer churn prediction in telecommunications. Expert Systems with Applications 39(1): 1414–1425.CrossRefGoogle Scholar
  20. Im J-K, Apley DW, Qi C and Shan X (2012). A timedependent proportional hazards survival model for credit risk analysis. Journal of Operational Research Society 63(3): 306–321.CrossRefGoogle Scholar
  21. Kim H-S and Yoon C-H (2004). Determinants of subscriber churn and customer loyalty in the Korean mobile telephony market. Telecommunications Policy 28(9–10): 751–765.CrossRefGoogle Scholar
  22. Kleinbaum DG and Klein M (2005). Survival Analysis: A Self-Learning Text. Springer: New York.Google Scholar
  23. Lam SY, Shankar V, Erramilli MK and Murthy B (2009). Customer value, satisfaction, loyalty, and switching costs: An illustration from a business-to-business service context. Journal of the Academy of Marketing Science 32(3): 293–311.CrossRefGoogle Scholar
  24. Lima E, Mues C and Baesens B (2009). Domain knowledge integration in data mining using decision tables: Case studies in churn prediction. Journal of Operational Research Society 60(8): 1096–1106.CrossRefGoogle Scholar
  25. Lin DY (2007). On the Breslow estimator. Lifetime Data Analysis 13(4): 471–480.CrossRefGoogle Scholar
  26. Liu D-R and Shih M-J (2010). Hybrid-patent classification based on patent-network analysis. Journal of the American Society for Information Science and Technology 62(2): 246–256.CrossRefGoogle Scholar
  27. Lu Q and Getoor L (2003). Link-based classification using labeled and unlabeled data. In: Proceedings of the ICML Workshop on The Continuum from Labeled to Unlabeled Data, ICML: Washington DC.Google Scholar
  28. Macskassy SA and Provost F (2003). A simple relational classifier. In: Proceedings of the Second Workshop on Multi-Relational Data Mining (MRDM-2003) at KDD-2003. ACM: New York, NY, pp 64–76.Google Scholar
  29. Macskassy SA and Provost F (2007). Classification in networked data: A toolkit and a univariate case study. Journal of Machine Learning Research 8(2): 935–983.Google Scholar
  30. McPherson M, Smith-Lovin L and Cook JM (2001). Birds of a feather: Homophily in social networks. Annual Review of Sociology 27(1): 415–444.CrossRefGoogle Scholar
  31. Mertens F, Saint-Charles J and Mergler D (2012). Social communication network analysis of the role of participatory research in the adoption of new fish consumption behaviors. Social Science and Medicine 75(4): 643–650.CrossRefGoogle Scholar
  32. Neslin SA, Gupta S, Kamakura W, Lu J and Mason CH (2006). Defection detection: Measuring and understanding the predictive accuracy of customer churn models. Journal of Marketing Research 43(2): 204–211.CrossRefGoogle Scholar
  33. Nitzan I and Libai B (2011). Social effects on customer retention. Journal of Marketing 75(6): 24–38.CrossRefGoogle Scholar
  34. Owczarczuk M (2010). Churn models for prepaid customers in the cellular telecommunication industry using large data marts. Expert Systems with Applications 37(6): 4710–4712.CrossRefGoogle Scholar
  35. Pendharkar PC (2009). Genetic algorithm based neural network approaches for predicting churn in cellular wireless network services. Expert Systems with Applications 36(3): 6714–6720.CrossRefGoogle Scholar
  36. Pow J, Gayen K, Elliott L and Raeside R (2012). Understanding complex interactions using social network analysis. Journal of Clinical Nursing 21(19–20): 2772–2779.CrossRefGoogle Scholar
  37. Rhodes CJ and Jones P (2009). Inferring missing links in partially observed social networks. Journal of Operational Research Society 60(10): 1373–1383.CrossRefGoogle Scholar
  38. Richter Y, Yom-Tov E and Slonim N (2010). Predicting customer churn in mobile networks through analysis of social groups. In: Proceedings of the 2010 SIAM International Conference on Data Mining, SIAM: Columbus, OH, pp 732–741.Google Scholar
  39. Risselada H, Verhoef P and Bijmolt T (2010). Staying power of churn prediction models. Journal of Interactive Marketing 24(3): 198–208.CrossRefGoogle Scholar
  40. Rosenberg LJ and Czepiel JA (1984). A marketing approach for customer retention. Journal of Consumer Marketing 1(2): 45–51.CrossRefGoogle Scholar
  41. SAS Institute (2012). The PHREG Procedure. In SAS/ STATR_ 12.1 User’s Guide, SAS Institute: Cary, NC, pp 5541–5769.Google Scholar
  42. Ultsch A (2001). Emergent self-organising feature maps used for prediction and prevention of churn in mobile phone markets. Journal of Targeting, Measurement, and Analysis for Marketing 10(4): 314–324.CrossRefGoogle Scholar
  43. Verbeke W, Dejaeger K, Martens D, Hur J and Baesens B (2012). New insights into churn prediction in the telecommunication sector: A profit driven data mining approach. European Journal of Operational Research 218(1): 211–229.CrossRefGoogle Scholar
  44. Verbeke W, Martens D and Baesens B (2014). Social network analysis for customer churn prediction. Applied Soft Computing 14(Part C): 431–446.CrossRefGoogle Scholar
  45. Verbeke W, Martens D, Mues C and Baesens B (2011). Building comprehensible customer churn prediction models with advanced rule induction techniques. Expert Systems with Applications 38(3): 2354–2364.CrossRefGoogle Scholar
  46. Verbraken T, Verbeke W and Baesens B (2013). A novel profit maximizing metric for measuring classification performance of customer churn prediction models. IEEE Transactions on Knowledge and Data Engineering 25(5): 961–973.CrossRefGoogle Scholar
  47. Wei C-P and Chiu I-T (2002). Turning telecommunications call details to churn prediction: A data mining approach. Expert Systems with Applications 23(2): 103–112.CrossRefGoogle Scholar
  48. Wong K.K.-K. (2011). Using Cox regression to model customer time to churn in the wireless telecommunications industry. Journal of Targeting, Measurement, and Analysis for Marketing 19(1): 37–43.CrossRefGoogle Scholar
  49. Zhang X, Zhu J, Xu S and Wan Y (2012). Predicting customer churn through interpersonal influence. Knowledge-Based Systems 28(1): 97–104.CrossRefGoogle Scholar
  50. Zuashkiani A, Banjevic D and AKS Jardine (2005). Estimating parameters of proportional hazards model based on expert knowledge and statistical data. Journal of Operational Research Society 60(12): 1621–1636.CrossRefGoogle Scholar

Copyright information

© The Operational Research Society 2016

Authors and Affiliations

  • Aimée Backiel
    • 1
    Email author
  • Bart Baesens
    • 1
    • 2
    • 3
  • Gerda Claeskens
    • 1
  1. 1.Katholieke Universiteit LeuvenLeuvenBelgium
  2. 2.University of SouthamptonHighfield SouthamptonUK
  3. 3.Vlerick, Leuven-Gent Management SchoolGentBelgium

Personalised recommendations