Hostname: page-component-76fb5796d-vvkck Total loading time: 0 Render date: 2024-04-26T07:16:11.141Z Has data issue: false hasContentIssue false
  • English
  • Français

A spatial machine learning model for analysing customers’ lapse behaviour in life insurance

Published online by Cambridge University Press:  10 November 2020

Sen Hu ,
Adrian O’Hagan ,
James Sweeney  and
Mohammadhossein Ghahramani
Sen Hu
Affiliation:
Insight Centre for Data Analytics, University College Dublin, Ireland School of Mathematics and Statistics, University College Dublin, Ireland
Adrian O’Hagan*
Affiliation:
Insight Centre for Data Analytics, University College Dublin, Ireland School of Mathematics and Statistics, University College Dublin, Ireland
James Sweeney
Affiliation:
Department of Mathematics and Statistics, University of Limerick, Ireland
Mohammadhossein Ghahramani
Affiliation:
Insight Centre for Data Analytics, University College Dublin, Ireland School of Mathematics and Statistics, University College Dublin, Ireland
*
*Corresponding author. E-mail: adrian.ohagan@ucd.ie
Get access Rights & Permissions [Opens in a new window]

Abstract

Spatial analysis ranges from simple univariate descriptive statistics to complex multivariate analyses and is typically used to investigate spatial patterns or to identify spatially linked consumer behaviours in insurance. This paper investigates if the incorporation of publicly available spatially linked demographic census data at population level is useful in modelling customers’ lapse behaviour (i.e. stopping payment of premiums) in life insurance policies, based on data provided by an insurance company in Ireland. From the insurance company’s perspective, identifying and assessing such lapsing risks in advance permit engagement to prevent such incidents, saving money by re-evaluating customer acquisition channels and improving capital reserve calculation and preparation. Incorporating spatial analysis in lapse modelling is expected to improve lapse prediction. Therefore, a hybrid approach to lapse prediction is proposed – spatial clustering using census data is used to reveal the underlying spatial structure of customers of the Irish life insurer, in conjunction with traditional statistical models for lapse prediction based on the company data. The primary contribution of this work is to consider the spatial characteristics of customers for life insurance lapse behaviour, via the integration of reliable government provided census demographics, which has not been considered previously in actuarial literature. Company decision-makers can use the insights gleaned from this analysis to identify customer subsets to target with personalized promotions to reduce lapse rates, and to reduce overall company risk.

Keywords

ClusteringLife insurance modellingLogistic regressionMachine learningSpatial analysisCensus data
Type
Paper
Information
Annals of Actuarial Science , Volume 15 , Issue 2 , July 2021 , pp. 367 - 393
Copyright
© The Author(s), 2020. Published by Cambridge University Press on behalf of Institute and Faculty of Actuaries

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Adams, M., Andersson, L.F., Lindmark, M., Eriksson, L. & Veprauskaite, E. (2020). Managing policy lapse risk in Sweden’s life insurance market between 1915 and 1947. Business History, 62(2), 222–239.CrossRefGoogle Scholar
Awang, M.K., Rahman, M.N.A. & Ismail, M.R. (2012). Data mining for churn prediction: multiple regressions approach. In Kim, T., Ma, J., Fang, W., Zhang, Y. & Cuzzocrea, A. (Eds.), Computer Applications for Database, Education, and Ubiquitous Computing (pp. 318–324). Springer Berlin Heidelberg, Berlin, Heidelberg.CrossRefGoogle Scholar
Bradley, A.P. (1997). The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition, 30(7), 1145–1159.CrossRefGoogle Scholar
Brunsdon, C., Charlton, M. & Rigby, J.E. (2018). An open source geodemographic classification of small areas in the Republic of Ireland. Applied Spatial Analysis and Policy, 11(2), 183–204.CrossRefGoogle Scholar
Calka, B. (2019). Estimating residential property values on the basis of clustering and geostatistics. 9(3), 143.Google Scholar
Cerchiara, R.R., Gambini, A. & Edwards, M. (2009). Generalized linear models in life insurance: decrements and risk factor analysis under Solvency II. Giornale dell’Istituto Italiano degli Attuari.Google Scholar
Coussement, K., Benoit, D.F. & Van den Poel, D. (2015). Preventing customers from running away! Exploring generalized additive models for customer churn prediction. In Dato-on, M.C. (Ed.), The Sustainable Global Marketplace (p. 238). Springer International Publishing.CrossRefGoogle Scholar
Cox, S.H. & Lin, Y. (2006). Annuity lapse rate modeling: tobit or not tobit? Risk management research projects: policyholder behavior in the tail project – annuity lapse modeling. Society of Actuaries.Google Scholar
Dong, Y., Chawla, N.V., Tang, J., Yang, Y. & Yang, Y. (2017). User modeling on demographic attributes in big mobile social networks. ACM Transactions on Information Systems, 35(4), 1–33.CrossRefGoogle Scholar
Eling, M. & Kiesenbauer, D. (2014), What policy features determine life insurance lapse? An analysis of the German market. The Journal of Risk and Insurance, 81(2), 241–269.CrossRefGoogle Scholar
Eling, M. & Kochanski, M. (2013). Research on lapse in life insurance: what has been done and what needs to be done? The Journal of Risk Finance, 14(4), 392–413.CrossRefGoogle Scholar
Fier, S.G. & Liebenberg, A.P. (2013). Life insurance lapse behavior. North American Actuarial Journal, 17(2), 153–167.CrossRefGoogle Scholar
Ghahramani, M., Zhou, M. & Hon, C.T. (2019). Mobile phone data analysis: a spatial exploration toward hotspot detection. IEEE Transactions on Automation Science and Engineering, 16(1), 351–362.CrossRefGoogle Scholar
Hand, D.J. & Till, R.J. (2001). A simple generalisation of the area under the ROC curve for multiple class classification problems. Machine Learning, 45(2), 171–186.CrossRefGoogle Scholar
Hanley, J.A. & McNeil, B.J. (1982). The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 143(1), 29–36.CrossRefGoogle Scholar
Kaufman, L. & Rousseeuw, P.J. (1990). Finding Groups in Data: An Introduction to Cluster Analysis, Wiley Series in Probability and Statistics, Wiley, Hoboken, New Jersey, USA.CrossRefGoogle Scholar
Kaufmann, L. & Rousseeuw, P. (1987). Clustering by means of medoids. Data Analysis Based on the L1-Norm and Related Methods, 405–416.Google Scholar
Kiesenbauer, D. (2012). Main determinants of lapse in the German life insurance industry. North American Actuarial Journal, 16(1), 52–73.CrossRefGoogle Scholar
Kim, C. (2005). Modeling surrender and lapse rates with economic variables. North American Actuarial Journal, 9(4), 56–70.CrossRefGoogle Scholar
Kim, C. (2006). Report to the policyholder behaviour in the tail subgroups project. Society of Actuaries. Google Scholar
Lamnisos, D., Middleton, N., Kyprianou, N. & Talias, M.A. (2019). Geodemographic area classification and association with mortality: an ecological study of small areas of Cyprus. International Journal of Environmental Research and Public Health, 16(16), 2927–2940.CrossRefGoogle ScholarPubMed
Li, G. & Deng, X. (2012). Customer churn prediction of China Telecom based on cluster analysis and decision tree algorithm. In Lei, J., Wang, F.L., Deng, H. & Miao, D. (Eds.), Emerging Research in Artificial Intelligence and Computational Intelligence (pp. 319–327), Springer Berlin Heidelberg, Berlin, Heidelberg.CrossRefGoogle Scholar
Loisel, S., Piette, P. & Tsai, J. (2019). Applying economic measures to lapse risk management with machine learning approaches, arXivpreprint:1906.05087.Google Scholar
Milhaud, X., Loisel, S. & Maume-Deschamps, V. (2011). Surrender triggers in life insurance: what main features affect the surrender behavior in a classical economic context? Bulletin Français d’Actuariat, Institut des Actuaires, 11(22), 5–48.Google Scholar
Singh, D. & Singh, B. (2019). Investigating the impact of data normalization on classification performance. Applied Soft Computing, 105524.Google Scholar
Tiwari, A., Hadden, J. & Turner, C. (2010). A new neural network based customer profiling methodology for churn prediction. In Taniar, D., Gervasi, O., Murgante, B., Pardede, E. & Apduhan, B.O. (Eds.), Computational Science and Its Applications – ICCSA 2010 (pp. 358–369). Springer Berlin Heidelberg, Berlin, Heidelberg.CrossRefGoogle Scholar