Bonus-Malus Systems In Automobile Insurance

Bonus-Malus Systems(BMS)are the most common forms of a posteriori ratemaking in automobile third-party liability insurance.In the next payment,policyholders who submitted one or more claims will be penalized by premium raise(malus),while policyholders who submitted no claim will be rewarded by premium reduction(bonus).Previous research about Bonus-Malus Systems concern with the determination of the risk premium which are mostly based on the number of claims.The aim of this paper is to represent the fundamental principle and operating mechanism of Bonus-Malus Systems,specific research contents and the results obtained are as follows:1.Superpose distribution and zero inflated distribution are developed as an alternative to traditionally Poisson distribution methods to fit the claim numbers on homogeneous policyholders.As there are usually a relatively large number of zeros(no-claims)while modeling claim counts collected from auto insurance manufacturing processes.2.Utilizing INAR(1)model to fit and predict the claim frequency through time series methods,underlying the idea of the mathematical definition and rating migration regulation of BMS.3.Providing an overall introduction of the classic Bonus-Malus System model,including the claim frequency probability,the construction of an optimal BMS,the variety of premium calculation principle,etc.4.Considering the restriction of the traditional BMS model,delivering a concept of large-size claim,which are applied to modify bonus-malus system with claim severity.5.Offering several proposal improvements about the design and operating mechanism of BMS,such as organizing a path-dependent BMS,combining peccancy recording to BMS,and establishing an information sharing platform against penalty escape tendency.