Abstract: Novel navigation applications provide a driving behavior score for each finished trip to promote safe driving, which is mainly based on experts' domain knowledge. In this paper, with automobile insurance claims data and associated telematics car driving data, we propose a supervised driving risk scoring neural network model. This one-dimensional convolutional neural network takes time series of individual car driving trips as input and returns a risk score in the unit range of (0, 1). By incorporating credibility average risk score of each driver, the classical Poisson generalized linear model for automobile insurance claims frequency prediction can be improved significantly. Hence, compared with non-telematics-based insurers, telematics-based insurers can discover more heterogeneity in their portfolio and attract safer drivers with premiums discounts.
About: Dr. Guangyuan Gao is an Associate Professor in the School of Statistics at the Renmin University of China. He obtained his Phd in Statistics at the Australian National University in 2016. Before that, he obtained his bachelor in Engineering at Tongji University in Shanghai. His research interests include non-life insurance claims reserving, mortality forecasting, telematics car driving data analysis, automobile insurance pricing, Bayesian statistics, etc. His research work has been published in ASTIN, SAJ, IME, NAAJ, etc. He is in charge of a National Natural Science Foundation of China.
(If there is a problem with the URL, please try to join the meeting with Meeting ID and Password.)
Meeting ID: 792 221 9559