A Markov-modulated tree-based gradient boosting model for auto-insurance risk premium pricing

In most sub Saharan African countries,the mechanism for pricing auto-insurance policies is tariff based. This means that the key factor that influences price changes is usually based on regulation and legislative dynamics. Additionally, where ratemaking is risk based, analysis has in most cases focused on internal historical data or claims history, particularly in the sub Saharran Africa. These policy regimes have led to unfair price distortions among policyholders and have increased risk of portfolios for most insurance companies. In this study we consider geographical location risk that influence auto-insurance claim process for an insurance company. The study develops a Markov-modulated tree-based gradient boosting (MMGB) model for pricing auto-insurance premiums. The Markov-modulated tree-based gradient boosting model is a Tweedie general linear model (GLM) based pricing algorithm with a compound Poisson-Gamma distribution whose rate varies according to accident risk in a Markovian process. Thus, the study extends the existing premium pricing framework by integrating a geographical location risk factor into the main pricing framework. The study applies the model to a motor insurance data set from Ghana. The results show that the proposed method is superior to other competing models because it generates relatively fair premium predictions for the non-life auto-insurance companies, helping to mitigate more the insured risk for the firm and the industry.