Usage-based Insurance Ratemaking Method based on Risk Probability

• 1、School of Economics and Management, Beijing University of Posts and Telecommunications,Beijing 100876
• 2、School of Business and Management, Shanghai International Studies University,Shanghai 201620

Abstract：With the deepening of the reform of commercial vehicle insurance rate and the continuous development of Internet of vehicles technology, it has become the development trend of vehicle insurance industry to develop personalized and differentiated vehicle insurance products based on driving behavior data. Based on the driving risk factors extracted from the real driving behavior data, this paper establishes three kinds of risk probability prediction models to systematically evaluate the driver\'s risk, and determines the driver\'s risk level in the whole group according to the clustering algorithm, so as to carry out differential pricing of vehicle insurance. The results show that: the introduction of driving behavior factor can effectively evaluate the risk level of drivers. At the same time, after the driver behavior is included in the vehicle insurance rate, the rate of commercial vehicle insurance is more matched with the driving risk, and the pricing of vehicle insurance is more fair and reasonable.

Keywords： Usage-based Insurance Risk Probability Vehicle Insurance Ratemaking Machine Learning