OPTIMAL BONUS-MALUS SYSTEMS USING FINITE MIXTURE MODELS. Issue 2 (10th January 2014)

• Record Type: Journal Article
• Authors: Tzougas, George; Vrontos, Spyridon; Frangos, Nicholas
• Is Part Of: ASTIN bulletin. Volume 44:Issue 2(2014)
• Page Start: 417
• Page End: 444
• Publication Date: 2014-01-10
• Subjects: Insurance -- Mathematics -- Periodicals; Risk (Insurance) -- Mathematics -- Periodicals; 368.01
• DOI: 10.1017/asb.2013.31
• Languages: English
• ISSNs: 0515-0361

Abstract

<abstract abstract-type="normal"> <title>Abstract</title> <p>This paper presents the design of optimal Bonus-Malus Systems using finite mixture models, extending the work of Lemaire (1995; <sc>Lemaire</sc>, J. (1995) <italic>Bonus-Malus Systems in Automobile Insurance</italic>. Norwell, MA: Kluwer) and Frangos and Vrontos (2001; <sc>Frangos</sc>, N. and <sc>Vrontos</sc>, S. (2001) Design of optimal bonus-malus systems with a frequency and a severity component on an individual basis in automobile insurance. <italic>ASTIN Bulletin</italic>, <bold>31</bold>(1), 1–22). Specifically, for the frequency component we employ finite Poisson, Delaporte and Negative Binomial mixtures, while for the severity component we employ finite Exponential, Gamma, Weibull and Generalized Beta Type II mixtures, updating the posterior probability. We also consider the case of a finite Negative Binomial mixture and a finite Pareto mixture updating the posterior mean. The generalized Bonus-Malus Systems we propose, integrate risk classification and experience rating by taking into account both the a priori and a posteriori characteristics of each policyholder.</p> </abstract>