Fuzzy risk mode and effect analyasis based on raw driving data for pay-how-you-drive vehicle insurance

Pay-how-you-drive (PHYD), which has already been recognized as the most promising differentiated commercial vehicle insurance product in usage based insurance (UBI), can objectively analyze the risk level of each insured vehicle by analyzing its driving style from raw data collected by on-board diagnosis (OBD) module set up on it. Finding certain kinds of driving styles, or risk modes from raw data for insured vehicles, is very important for the insurance companies to get a rough understand of the types of each contract holders and to do the preliminary premium actuary work. Consider that there is a lack of theory basis for driving styles, or risk modes identification and their effect analysis in quantity, in this paper, in order to quantify the effect of different risk modes, and consider that the effect evaluation might be under fuzzy or uncertainty conditions, a fuzzy risk mode and effect analysis (FRMEA) method which can be applied in the early stage of premium actuary for PHYD insurance product is proposed, by setting 4 key indices including occurrence, severity, testability and preventability, and by referencing the grading results from a group of experts, the effect grades of several different risk modes have been given and described via fuzzy triangular numbers.