×

Multivariate modelling of household claim frequencies in motor third-party liability insurance. (English) Zbl 1416.91214

Summary: Actuarial risk classification studies are typically confined to univariate, policy-based analyses: Individual claim frequencies are modelled for a single product, without accounting for the interactions between the different coverages bought by the members of the same household. Now that large amounts of data are available and that the customer’s value is at the heart of insurers’ strategies, it becomes essential to develop multivariate risk models combining all the products subscribed by the members of the household in order to capture the correlation effects. This paper aims to supplement the standard actuarial policy-based approach with a household-based approach. This makes the actuarial model more complex but also increases the volume of available information which eases and refines forecasting. Possible cross-selling opportunities can also be identified.

MSC:

91B30 Risk theory, insurance (MSC2010)
62P05 Applications of statistics to actuarial sciences and financial mathematics
62H05 Characterization and structure theory for multivariate probability distributions; copulas
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Antonio, K.; Guillen, M.; Perez Martin, A. M., (2011)
[2] Barseghyan, L.; Molinari, F.; Morris, D. S.; Teitelbaum, J. C., (2016)
[3] Bühlmann, H.; Gisler, A., A Course in Credibility Theory and its Applications, (2005), Berlin: Springer, Berlin · Zbl 1108.91001
[4] Denuit, M.; Dhaene, J.; Goovaerts, M. J.; Kaas, R., Actuarial Theory for Dependent Risks: Measures, Orders and Models, (2005), New York: Wiley, New York
[5] Denuit, M.; Lang, S., Non-life rate-making with Bayesian GAMs, Insurance: Mathematics and Economics, 35, 627-647, (2004) · Zbl 1070.62095
[6] Denuit, M.; Marechal, X.; Pitrebois, S.; Walhin, J.-F., Actuarial Modelling of Claim Counts: Risk Classification, Credibility and Bonus-Malus Systems, (2007), New York: Wiley, New York · Zbl 1168.91001
[7] Englund, M.; Guillen, M.; Gustafsson, J.; Nielsen, L. H.; Nielsen, J. P., Multivariate latent risk: A credibility approach., ASTIN Bulletin, 38, 137-146, (2008) · Zbl 1169.91387 · doi:10.1017/S0515036100015099
[8] Englund, M.; Gustafsson, J.; Nielsen, L. H.; Nielsen, J. P., Multidimensional credibility with time effects: An application to commercial business lines., Journal of Risk and Insurance, 76, 443-453, (2009) · doi:10.1111/j.1539-6975.2009.01306.x
[9] Fardilha, T.; De Lourdes Centeno, M.; Esteves, R., Tariff systems for fleets of vehicles: A study on the portfolio of Fidelidade., European Actuarial Journal, 6, 331-349, (2016) · Zbl 1394.91214 · doi:10.1007/s13385-016-0138-7
[10] Frees, E. W.J.; Meyers, G.; Cummings, A. D., Dependent multi-peril ratemaking models., ASTIN Bulletin, 40, 699-726, (2010) · Zbl 1235.91088
[11] Kroeze, K., (2016)
[12] Narasimhan, B., (2016)
[13] Shi, P., Insurance ratemaking using a copula-based multivariate Tweedie model., Scandinavian Actuarial Journal, 2016, 198-215, (2016) · Zbl 1401.91194 · doi:10.1080/03461238.2014.921639
[14] Shi, P.; Feng, X.; Boucher, J. P., Multilevel modeling of insurance claims using copulas., Annals of Applied Statistics, 10, 834-863, (2016) · Zbl 1400.62238 · doi:10.1214/16-AOAS914
[15] Shi, P.; Valdez, E. A., Multivariate negative binomial models for insurance claim counts., Insurance: Mathematics and Economics, 55, 18-29, (2014) · Zbl 1296.91169
[16] Thuring, F.; Nielsen, J. P.; Guillen, M.; Bolance, C., Selecting prospects for cross-selling financial products using multivariate credibility., Expert Systems with Applications, 39, 8809-8816, (2012) · doi:10.1016/j.eswa.2012.02.011
[17] Weiser, C., (2016)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.