朴素贝叶斯算法与车辆风险分类  

Naive Bayesian algorithm and auto-insurance risk classification

作　　者：郭念国[1] GUO Nian-guo(College of Science,Henan University of Technology,Zhengzhou 450001,China)

机构地区：[1]河南工业大学理学院,河南郑州450001

出　　处：《河南城建学院学报》2020年第3期87-92,共6页Journal of Henan University of Urban Construction

基　　金：河南省高等学校重点科研项目(19A910001)。

摘　　要：车辆保险中分类费率厘定的目标之一就是保费能够正确反映风险的大小,而对风险分类是分类费率厘定的基础。基于朴素贝叶斯算法,对车辆保险领域中的索赔风险进行分类并与常用的广义线性模型拟合结果进行比较。结果表明:采用朴素贝叶斯算法对索赔风险进行分类预测是可行的。One of the objectives of the classification rate determination is to hope that the premium can correctly reflect the level of the risk,and the risk classification is the first step of the rate setting.Based on naive Bayesian algorithm,this paper classifies and predicts the claim risks in the field of auto-insurance,and compares the fitting results with the generalized linear model to show that it is feasible to predict the claim risk by naive Bayesian algorithm.

关 键 词：朴素贝叶斯算法 风险分类 车辆保险 

分 类 号：O212[理学—概率论与数理统计]