Abstract
Life insurance faces a number of new challenges. This paper identifies some difficulties with techniques that are widely used to cope with these challenges. As an interesting alternative tree-based methods are suggested and discussed. In particular a “hybrid” approach (using regression trees for a classification situation) is proposed. The main advantage of this approach is its ease of interpretability and its inherent transparency. The method appears to be particularly suitable for the identification of the risk factors in complex situations like disability insurance.
Similar content being viewed by others
References
Bauer M, Krüger R, Olbricht W (2011) Tree-based methods: an application to disability probabilities 16 pp (to be submitted)
Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth, Boca Raton
Cox DR (1972) Regression models and life-tables. J R Stat Soc B 34(2):187–220
DAV-Unterarbeitsgruppe Todesfallrisiko (2009) Herleitung der Sterbetafel DAV 2008 T für Lebensversicherungen mit Todesfallcharakter. Blätter der DGVFM 30:189–224
Hastie T, Tibshirani R, Friedman J (2001) The elements of statistical learning. Springer, New York
Huber PJ (2011) Data analysis: what can be learned from the past 50 years. John Wiley & Sons, Hoboken
Izenman AJ (2008) Modern multivariate statistical techniques. Springer, New York
Venables WN, Ripley BD (2002) Modern applied statistics with S, 4th edn. Springer, New York
Acknowledgments
The author is grateful to Swiss Re for their support and for providing the data set used in the example in Sect. 4.3 from their data monitoring pool and in particular to Marcus Bauer and Ralf Krüger of Swiss Re for performing the calculations behind Fig. 8 and Table 6. He would like to thank the participants of the data monitoring pool workshops for many stimulating and helpful discussions. Thanks go also to Wayne Dam of Swiss Re for checking the English and for suggesting a number of stylistic improvements, to the organizers of the ‘DAV-Herbsttagung 2010’ for the invitation to present part of the material of this paper there, and to the reviewer for his useful and constructive suggestions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Olbricht, W. Tree-based methods: a useful tool for life insurance. Eur. Actuar. J. 2, 129–147 (2012). https://doi.org/10.1007/s13385-012-0045-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13385-012-0045-5