Random Forests for Uplift Modeling: An Insurance Customer Retention Case

  • Leo Guelman
  • Montserrat Guillén
  • Ana M. Pérez-Marín
Part of the Lecture Notes in Business Information Processing book series (LNBIP, volume 115)


Models of customer churn are based on historical data and are used to predict the probability that a client switches to another company. We address customer retention in insurance. Rather than concentrating on those customers with high probability of leaving, we propose a new procedure that can be used to identify the target customers who are likely to respond positively to a retention activity. Our approach is based on random forests and can be useful to anticipate the success of marketing actions aimed at reducing customer attrition. We also discuss the type of insurance portfolio database that can be used for this purpose.


Random Forest Switching Cost Customer Loyalty Insurance Industry Loyalty Strategy 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kotler, P.: Marketing during periods of shortage. J. Marketing 38(3), 20–29 (1974)CrossRefGoogle Scholar
  2. 2.
    Kamakura, W.A., Ramaswami, S., Srivastava, R.: Applying latent trait analysis in the evaluation of prospects for cross-selling of financial services. Int. J. Res. Mark. 8, 329–349 (1991)CrossRefGoogle Scholar
  3. 3.
    Seng, J.-L., Chen, T.C.: An analytical approach to select data mining for business decision. Expert Syst. Appl. 37(9), 8042–8057 (2010)CrossRefGoogle Scholar
  4. 4.
    Liao, S.-H., Chen, Y.-J., Hsieh, H.-H.: Mining customer knowledge for direct selling and marketing. Expert Syst. Appl. 38(5), 6059–6069 (2011)CrossRefGoogle Scholar
  5. 5.
    Larivière, B., Van den Poel, D.: Predicting customer retention and profitability by using random forest and regression techniques. Expert Syst. Appl. 29(2), 472–484 (2005)CrossRefGoogle Scholar
  6. 6.
    Hammond, J.D., Houston, D.B., Melander, E.R.: Determinants of household life insurance premium expenditures: an empirical investigation. J. Risk Insur. 34(3), 397–408 (1967)CrossRefGoogle Scholar
  7. 7.
    Duker, J.M.: Expenditures for life insurance among working-wife families. J. Risk Insur. 36(5), 525–533 (1969)CrossRefGoogle Scholar
  8. 8.
    Mayers, D., Smith Jr., C.W.: The interdependence of individual portfolio decisions and the demand for insurance. J. Polit. Econ. 91(2), 304–311 (1983)CrossRefGoogle Scholar
  9. 9.
    Doherty, N.A.: Portfolio efficient insurance buying strategies. J. Risk Insur. 51(2), 205–224 (1984)CrossRefGoogle Scholar
  10. 10.
    Crosby, L.A., Stephens, N.: Effects of relationship marketing on satisfaction, retention, and prices in the life insurance industry. J. Marketing Res. 24(4), 404–411 (1987)CrossRefGoogle Scholar
  11. 11.
    Jackson, D.: Determining a customers lifetime value, part three. Direct Marketing 52(4), 28–30 (1989)Google Scholar
  12. 12.
    Berger, P.D., Nasr, N.: Customer lifetime value: marketing models and applications. J. Interact. Mark. 12, 17–30 (1998)CrossRefGoogle Scholar
  13. 13.
    Schlesinger, H., Schulenburg, J.M.: Customer information and decisions to switch insurers. J. Risk Insur. 60(4), 591–615 (1993)CrossRefGoogle Scholar
  14. 14.
    Cooley, S.: Loyalty strategy development using applied member-cohort segmentation. J. Consum. Mark. 19(7), 550–563 (2002)CrossRefGoogle Scholar
  15. 15.
    Ryals, L.J., Knox, S.: Measuring risk-adjusted customer lifetime value and its impact on relationship marketing strategies and shareholder value. Eur. J. Marketing 39(5/6), 456–472 (2005)CrossRefGoogle Scholar
  16. 16.
    Brockett, P.L., Golden, L., Guillén, M., Nielsen, J.P., Parner, J., Pérez-Marín, A.M.: Survival analysis of household insurance policies: How much time do you have to stop total customer defection? J. Risk Insur. 75(3), 713–737 (2008)CrossRefGoogle Scholar
  17. 17.
    Guillén, M., Nielsen, J.P., Pérez-Marín, A.M.: The need to monitor customer loyalty and business risk in the European insurance industry. Geneva Pap. R. I. – Iss. P. 33, 207–218 (2008)CrossRefGoogle Scholar
  18. 18.
    Guillén, M., Pérez-Marín, A.M., Alcaniz, M.: A logistic regression approach to estimating customer profit loss due to lapses in insurance. Insurance Markets and Companies: Analyses and Actuarial Computations 2(2), 42–54 (2011)Google Scholar
  19. 19.
    Guillén, M., Nielsen, J.P., Scheike, T.H., Pérez-Marín, A.M.: Time-varying effects in the analysis of customer loyalty: A case study in insurance. Expert Syst. Appl. 39, 3551–3558 (2012)CrossRefGoogle Scholar
  20. 20.
    Lai, L.-H., Liu, C.T., Lin, J.T.: The moderating effects of switching costs and inertia on the customer satisfaction-retention link: auto liability insurance service in Taiwan. Insurance Markets and Companies: Analyses and Actuarial Computations 2(1), 69–78 (2011)Google Scholar
  21. 21.
    Neslin, S., Gupta, S., Kamakura, W., Lu, J., Mason, C.: Defection detection: Measuring and understanding the predictive accuracy of customer churn model. J. Marketing Res. 43, 204–211 (2006)CrossRefGoogle Scholar
  22. 22.
    Lemmens, A., Croux, C.: Bagging and boosting classification trees to predict churn. J. Marketing Res. 43, 276–286 (2006)CrossRefGoogle Scholar
  23. 23.
    Coussement, K., Van den Poel, D.: Churn prediction in subscription services: An application of support vector machines while comparing two parameter-selection techniques. Expert Syst. Appl. 34, 313–327 (2008)CrossRefGoogle Scholar
  24. 24.
    Hansotia, B., Rukstales, B.: Incremental value modeling. J. Interact. Mark. 16(3), 35–46 (2002)CrossRefGoogle Scholar
  25. 25.
    Lo, V.: The true lift model. ACM SIGKDD Explorations Newsletter 4(2), 78–86 (2002)CrossRefGoogle Scholar
  26. 26.
    Larsen, K.: Net models. In: M2009 - Annual SAS Data Mining Conference (2009) Google Scholar
  27. 27.
    Kass, G.: An exploratory technique for investigating large quantities of categorical data. Appl. Stat. – J. Roy. St. C 29(2), 119–127 (1980)CrossRefGoogle Scholar
  28. 28.
    Radcliffe, N., Surry, P.: Real-World Uplift Modelling with Significance-Based Uplift Trees. Portrait Technical Report, TR-2011-1 (2011) Google Scholar
  29. 29.
    Rzepakowski, P., Jaroszewicz, S.: Decision trees for uplift modeling with single and multiple treatments. Knowl. Inf. Syst. (2011), doi: 10.1007/s10115-011-0434-0Google Scholar
  30. 30.
    Breiman, L.: Bagging predictors. Mach. Learn. 26, 123–140 (1996)Google Scholar
  31. 31.
    Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning, 2nd edn. Springer, New York (2009)zbMATHCrossRefGoogle Scholar
  32. 32.
    Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)zbMATHCrossRefGoogle Scholar
  33. 33.
    Segal, M.: Machine learning benchmarks and random forest regression, Technical report, eScholarship Repository, University of California (2004),
  34. 34.
    Stauss, B., Schmidt, M., Schoeler, A.: Customer frustration in loyalty programs. Int. J. Serv. Ind. Manag. 16(3), 229–252 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Leo Guelman
    • 1
  • Montserrat Guillén
    • 2
  • Ana M. Pérez-Marín
    • 2
  1. 1.RBC InsuranceRoyal Bank of CanadaMississaugaCanada
  2. 2.RiskcenterUniversity of BarcelonaBarcelonaSpain

Personalised recommendations