Influence of male/female partition and mileage experience in auto insurance.

Summary In the automobile insurance sector, the decision of the Court of Justice of the European Union that it is no longer possible to charge rates according to the gender of the insured, as well as the spread of aukilo insurance schemes, necessarily lead to an evolution of risk management. In this article, we use the Allianz portfolio in France to address these two issues. We propose to characterize the male/female partition by exploring different statistical methods such as the logistic procedure, the multiple correspondence analysis (MCA) or the classification trees (CART). We show that it is possible to compensate for the absence of the sex variable by other information specific to the insured or to his vehicle and in particular the use of mileage records [11]. We then return to the use of generalized linear models (GLM) to validate these results. In a second part, we focus on the experience of novice drivers. This category of insureds is among the most sensitive to male/female criteria in its pricing. Here, Generalized Additive Models (GAM) are used to exploit numerical variables such as the annual mileage driven. Finally, we propose to study the on-road behavior of the insured during his three years of novitiate to create new risk categories.