Abstract
With the prevalence of GPS tracking technologiees, car insurance companies have started to adopt usage-based insurance policies, which adapt insurance premiums according to the customers' driving behavior. Although many risk models for assessing an individual driver's accident risk based on the history of driving trajectories, driving events, and exposure records exist, these models do not take the geographical context of the driven trajectories and driving events into account. This study explores the influence of enriching the existing purely driving-behavior-based feature set by multiple geographical context features for the task of differentiating between accident and accident-free drivers. Prediction performances of five machine learning classifiers—logistic regression, random forest, XGBoost, feed-forward neural networks (FFNN), and long short-term memory (LSTM) networks—were evaluated on the usage records of over 8000 vehicles in one year from Italy. The results show that the inclusion of geographical information such as weather, points of interest (POIs), and land use can increase the relative predictive performance in terms of AUC by up to 8%, among which land use is the most informative. For the data of this study, XGBoost generally yielded the best performance and made most use out of the geographical information, while logistic regression is only slightly outperformed by more complex models if the proposed geographical information is not available. LSTM did not outperform the other methods, possibly due to the small volume of training data available. The results outline the potential of including the geographical context in usage-based car insurance risk modeling to improve the accuracy, leading to fairer usage-based insurance policies.
Highlights
Every year around 1.35 million people die in road accidents, which today are the leading cause of death among children and young adults (WHO, 2020)
The results show that the inclusion of geographical information such as weather, points of interest (POIs), and land use can increase the relative predictive performance in terms of AUC by up to 8%, among which land use is the most informative
The private-owned vehicle GPS trajectory data set, with waypoints annotated with driving behavior and crash labels, was provided by the Track&Know Project1 funded by the European Horizon 2020 program
Summary
Every year around 1.35 million people die in road accidents, which today are the leading cause of death among children and young adults (WHO, 2020). A vast majority of these accidents are caused by human errors. In both the United States and Switzerland, around 94% of car accidents involve some form of human errors (National Highway Traffic Safety Administration, 2018; Swiss Federal Office of Statistics, 2018). Among the three main influencing factors of road safety—driver, road, and vehicle—driver is the most important and the hardest to change/improve Wang, Wu, & Li, 2015). Unsafe drivers need to be identified before turning them into safer drivers. The conventional self-report is not an optimal method for driver’s risk assessment as 80.3% of drivers self-describe their driving ability as above average (Nees, 2019)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
