Study of Piecewise UBI Pricing Strategy based on the Risk Probability
- DOI
- 10.2991/edmi-19.2019.9How to use a DOI?
- Keywords
- vehicle insurance, driving behavior analysis, the risk probability, probability distribution.
- Abstract
With the rapid growth of car ownership in China, vehicle insurance has become an important branch of the insurance industry. The traditional and single vehicle insurance premium pricing strategy is not conducive to the long-term development of the vehicle insurance industry. So, the Usage-Based Insurance (UBI) based on driving behavior analysis is put on the agenda. Based on the data collected by the real vehicle in the UBI pilot city where Dina Technology and an insurance company cooperate, this paper proposes a segmented UBI pricing strategy based on the distribution of risk probability. First, the user's driving behavior data are collected in real time through Dina Technology's intelligent vehicle On-Board Diagnostics (OBD) terminal. Then, the linear logistic regression machine learning algorithm is used to analyze the risk probability of the measured data, and determine the risk factor coefficients of each driving behavior. Finally, on the basis of the distribution function of the risk probability, the segmentation pricing is differentiated by setting the segmentation penalty factor. By supervising user's driving behavior to reward or punish, this strategy can improve the user's driving habits, improve the user's driving safety, and reduce the risk probability.
- Copyright
- © 2019, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Bo Huang AU - Junyuan Bian AU - Nanjie Liu PY - 2019/08 DA - 2019/08 TI - Study of Piecewise UBI Pricing Strategy based on the Risk Probability BT - Proceedings of the 1st International Symposium on Economic Development and Management Innovation (EDMI 2019) PB - Atlantis Press SP - 44 EP - 50 SN - 2352-5428 UR - https://doi.org/10.2991/edmi-19.2019.9 DO - 10.2991/edmi-19.2019.9 ID - Huang2019/08 ER -