Driving Risk Evaluation Based on Telematics Data

20 Pages Posted: 13 Dec 2018

See all articles by Guangyuan Gao

Guangyuan Gao

Renmin University of China - School of Statistics

Mario V. Wuthrich

RiskLab, ETH Zurich

Hanfang Yang

Renmin University of China - School of Statistics

Date Written: November 21, 2018

Abstract

Telematics car driving data describes drivers' driving characteristics. This paper studies the predictive power of telematics data for claims frequency prediction. We first extract covariates from telematics car driving data using K-mediods clustering and principal components analysis. These telematics covariates are then used as explanatory variables for claims frequency modeling, in which we analyze their predictive power. Moreover, we use these telematics covariates to challenge the classical covariates usually used.

Keywords: Telematics data; Driving habit; Driving style; v-a heatmap; Acceleration pattern; K-mediods algorithm; Principal components analysis; Generalized additive model; Generalized linear model; Variable selection; Collinearity; Poisson regression; Deviance statistics; Claims frequency modeling; Car

Suggested Citation

Gao, Guangyuan and Wuthrich, Mario V. and Yang, Hanfang, Driving Risk Evaluation Based on Telematics Data (November 21, 2018). Available at SSRN: https://ssrn.com/abstract=3288347 or http://dx.doi.org/10.2139/ssrn.3288347

Guangyuan Gao (Contact Author)

Renmin University of China - School of Statistics ( email )

No.59 Zhongguancun Street, Renmin University
Beijing, 100872
China

Mario V. Wuthrich

RiskLab, ETH Zurich ( email )

Department of Mathematics
Ramistrasse 101
Zurich, 8092
Switzerland

Hanfang Yang

Renmin University of China - School of Statistics ( email )

No.59 Zhongguancun Street, Renmin University
Beijing, 100872
China

Register to save articles to
your library

Register

Paper statistics

Downloads
31
Abstract Views
141
PlumX Metrics