Abstract
With the development of big data technologies, usage-based insurance (UBI) has received considerable attention from insurance companies. UBI products focus on identifying the relationship between the individual driver’s risk and online channel behavior variables from Internet of Vehicles (IoV) data. Although omnichannel information integration has promoted the development of many industries, it has not been used to improve the accuracy of driver risk classification models in insurance industries. This paper investigates the role of combining different channel variables in improving the classification of driver’s risk. Specifically, several models, including logistic regression and three different data mining techniques (neural networks, random forests, and support vector machines), augmented with driving behavior data based on the IoV and offline consumer behavior data collected from 4S (Sale, Spare part, Service, Survey) dealers, are applied to the classification model of risk. The empirical results show that the inclusion of online and offline channel data improves the different risk assessments; results also demonstrate the importance of offline consumer behavior variables in different models. These insights have important implications for insurance companies on UBI pricing strategy and cost management.
Highlights
Individual driving risk is characterized by substantial variation every year [1]
For the two new category variables, we find that adding offline consumer behavior variables to the basic model can significantly improve the accuracy of the crash risk classification, though the power of vehicles’ turning variables is relatively weak
For models using nonbinning data, all the results were better than random classification (AUC 0.50), which proves that the three types of collisions can be identified to a high level of performance based on these data
Summary
Individual driving risk is characterized by substantial variation every year [1]. According to the World Health Organization, approximately 1.35 million people die in traffic accidents every year, which means nearly 3,700 people die in traffic accidents every day [2]. Erefore, predicting crashes and identifying the factors related to individual driving risk classification will have great value for insurance companies. Due to limitations of data collection, early studies about crash risk classification focused on demographic variables, such as driver age and gender, and vehicle characteristics, such as vehicle age and color [4]. With the development of the Internet of ings (IoT), a massive flow of online channel data reflecting driving behavior has been generated, and this provides new opportunities to classify crashes. E new opportunities offer strong business decision-making support for insurance companies, especially in relation to usage-based insurance (or user behavior insurance) (UBI) [6, 7]. The price of UBI products is determined by individuals’ driving behavior collected from in-vehicle data records (IVDRs), which differs from the original UBI that used only vehicle usage information [8, 9]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
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 call