A Risky Driving Behavior Scoring Model for the Personalized Automobile Insurance Pricing

International Conference on Crowd Science and Engineering Pub Date : 2017-07-06 DOI:10.1145/3126973.3126978

Zhishuo Liu, Qianhui Shen, Han Li, Jingmiao Ma

{"title":"A Risky Driving Behavior Scoring Model for the Personalized Automobile Insurance Pricing","authors":"Zhishuo Liu, Qianhui Shen, Han Li, Jingmiao Ma","doi":"10.1145/3126973.3126978","DOIUrl":null,"url":null,"abstract":"Telematics1 techniques enable insurers to capture the driving behavior of policyholders and correspondingly offer the personalized vehicle insurance rate, namely the usage-based insurance (UBI). A risky driving behavior scoring model for the personalized automobile insurance pricing was proposed based on telematics data. Firstly, three typical UBI pricing modes were analyzed. Drive behavior rate factors (DBRF) pricing mode was proposed based on mileage rate factors (MRF), in which insurance rate for each vehicle can be determined by the evaluation of individual driving behavior using OBD data. Then, on the basis of the analysis of influencing factors of safe driving, a driving behavior score model was established for DBRF by the improved EW-AHP (Entropy Weight- Analytic Hierarchy Process) Method. Finally, driving behavior scores of 100 drivers were computed by using the data collected from a 6-month field experiment. The results of three statistics analysis showed that the driving behavior score model could effectively reflect the risk level of driver's safe driving and provide a basis for the individual discount or surcharge that insurers offer to their policyholders.","PeriodicalId":370356,"journal":{"name":"International Conference on Crowd Science and Engineering","volume":"13 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Crowd Science and Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3126973.3126978","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 7

Abstract

Telematics1 techniques enable insurers to capture the driving behavior of policyholders and correspondingly offer the personalized vehicle insurance rate, namely the usage-based insurance (UBI). A risky driving behavior scoring model for the personalized automobile insurance pricing was proposed based on telematics data. Firstly, three typical UBI pricing modes were analyzed. Drive behavior rate factors (DBRF) pricing mode was proposed based on mileage rate factors (MRF), in which insurance rate for each vehicle can be determined by the evaluation of individual driving behavior using OBD data. Then, on the basis of the analysis of influencing factors of safe driving, a driving behavior score model was established for DBRF by the improved EW-AHP (Entropy Weight- Analytic Hierarchy Process) Method. Finally, driving behavior scores of 100 drivers were computed by using the data collected from a 6-month field experiment. The results of three statistics analysis showed that the driving behavior score model could effectively reflect the risk level of driver's safe driving and provide a basis for the individual discount or surcharge that insurers offer to their policyholders.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

个性化汽车保险定价中的危险驾驶行为评分模型

远程信息处理技术使保险公司能够捕捉投保人的驾驶行为，并相应地提供个性化的车辆保险费率，即基于使用的保险(UBI)。提出了一种基于远程信息处理数据的个性化车险定价风险驾驶行为评分模型。首先，分析了三种典型的UBI定价模式。提出了基于里程费率因子(MRF)的驾驶行为费率因子(DBRF)定价模式，利用OBD数据对个体驾驶行为进行评价，确定每辆车的保险费率。然后，在分析安全驾驶影响因素的基础上，采用改进的EW-AHP(熵权-层次分析法)方法建立了DBRF驾驶行为评分模型。最后，利用为期6个月的现场实验数据，计算了100名驾驶员的驾驶行为得分。三次统计分析结果表明，驾驶行为评分模型能够有效反映驾驶员安全驾驶的风险水平，为保险公司向投保人提供个体折扣或附加费提供依据。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

International Conference on Crowd Science and Engineering

自引率

0.00%

发文量

期刊最新文献

A Study on Automatic Sleep Stage Classification Based on CNN-LSTM Forecasting Road Surface Temperature in Beijing Based on Machine Learning Algorithms An Intelligent Matching Algorithm of CDCI Model Automatic Segmentation of Left Myocardium in CMR Based on Fully Convolutional Networks LBTask: A Benchmark for Spatial Crowdsourcing Platforms