Claims Frequency Modeling  Using Telematics Car Driving Data
日期: 2018-07-20


Dr. Guangyuan Gao, a lecturer of Renmin University of China, graduated from the Australian National University School of Business, Institute of Finance, Actuarial and Applied Statistics, Ph.D. in Statistics; from 2010 to 2011, Master of Applied Statistics and Master of Actuarial Science from the Australian National University; Graduated from Tongji University. Research interests: non-life insurance reserve assessment model, vehicle network big data analysis, insurance reserve stochastic model, copulas and risk metrics.


We investigate the predictive power of covariates extracted from telematics car driving data using the speed-acceleration heatmaps of Gao and Wüthrich (2017). These telematics covariates include K-means classification, principal components, and bottleneck activations from a bottleneck neural network. It turns out that the first principal component and the bottleneck activations give a better out-of-sample prediction for claims frequencies than other traditional pricing factors such as driver's age. For this reason we recommend the use of these telematics covariates for car insurance pricing.