保险大数据条件下车险费率厘定的研究——基于SOM神经网络方法的车险索赔强度建模

A Research on the Rate Making of Automobile Insurance with Big Data——Modeling of automobile insurance claim severity based on SOM neural network

神经网络是近年来机器学习领域的研究热点之一。该方法在许多领域都有成功的应用,但较少应用于汽车保险索赔预测中。本研究将自组织竞争神经网络(SOM)应用于汽车保险的索赔预测中,在此基础上建立车险索赔强度模型。本研究将影响车险索赔的因素分为三类:从人因素、从车因素、地域因素。对于从车因素,通过应用SOM神经网络方法对多个解释变量进行聚类分析来获得综合影响评价指标——从车因子综合变量。进一步按照索赔强度的高低,将该变量分成5个水平,进而起到减少解释变量的作用。将地域因素作为随机效应,以从人因素变量和从车因子综合变量为自变量,以索赔强度为因变量,建立广义线性混合模型。本文创新在于:在充分考虑了影响车险费率的各种因素下,应用SOM神经网络聚类方法减少自变量的个数,为车险费率厘定提供了一种新思路。

Neural network is one of the research hotspots in the field of machine learning in recent years. This method has been successfully applied in many fields, however it is seldom used in automobile insurance claim pre- diction. In this paper, the self-organizing competitive neural network （SOM） was applied to the prediction of auto- mobile insurance losses, and the claim severity model of automobile insurance was established. The paper divided the factors affecting automobile insurance claims into three categories：human-related factors, automobile-related fac- tors and region-related factors. The multiple explanatory variables were clustered by SOM method to obtain the com- prehensive variables of the automobile-related factors. According to the extent of claim severity, these variables were then divided into five levels, which could reduce the explanatory variables. Region-related factors were used as ran- dom effects, and the comprehensive variables of automobile-related factors and human-related factors were intro- duced into the model as independent variables. The claim severity was regarded as dependent variable. The gener- alized linear mixed model was thus established. One of the advantages of this paper is that, while taking into ac- count all factors affecting automobile insurance rate making, the SOM clustering method reduces the number of inde- pendent variables,which provides a new vein of thought for automobile insurance claim pricing.