Bonus-Malus System Using Finite Mixture Models

Saeed MohammadPour, Karzan Saeedi, Rahim Mahmoudvand

Abstract


There is a vast literature on Bonus-Malus System (BMS), in which a policyholders responsible for positive claims will be penalised by a malus and the policyholders who had no claim will be rewarded by a bonus. In this paper, we present an optimal BMS using finite mixture models.  We conduct a numerical study to compare the new model with the current BMS that use finite mixture models.

Keywords


Bonus-Malus System, Mixture model, Bayes theorem

References


Denuit, M. and Ph. Lambert (2001). Smoothed NPML estimation of the risk distribution underlying Bonus-Malus systems. Proceedings of the Casualty Actuarial Society, 88, 142–174.

Frangos, N. and Vrontos, S. (2001) Design of optimal bonus-malus systems with a frequency and a severity component on an individual basis in automobile insurance. ASTIN Bulletin, 31, 1–22.

Gomez-Deniz, E., Vaquez-Polo, F.J., Perez-Sanchez, J.M. (2004). A note on mixture prior distributions with applications in actuarial statistic. Estudios de Economia Aplicada, 22 (2), 1–15.

Tzougas, G., Vrontos, S., and Frangos, N. (2014). Optimal Bonus-Malus Systems using Finite Mixture Models. ASTIN Bulletin, 44, 417–444.

Peter Macdonald and with contributions from Juan Du (2012). mixdist: Finite Mixture Distribution Models. R package version 0.5-4. http://CRAN.R-project.org/package=mixdist

Mahmoudvand, R., and Hassani, H. (2009). Generalized bonus-malus systems with a frequency and a severity component on an individual basis in automobile insurance. ASTIN Bulletin, 39(01), 307-315.

Mahmoudvand, R., Tan, C. & Abbasi, N. (2017). Adjusting the Premium Relativities in a Bonus-Malus System: An Integrated Approach Using the First Claim Time and the Number of Claims. Asia-Pacific Journal of Risk and Insurance, Forthcoming, doi:10.1515/apjri-2016-0038

Weinberg, G.V., Finch, D. (2012). Analysis of a Pareto Mixture Distribution for Maritime Surveillance Radar. Journal of Electrical and Computer Engineering, http://dx.doi.org/10.1155/2012/382979.


Full Text: PDF

DOI: 10.19139/soic.v5i3.264

Refbacks

  • There are currently no refbacks.