Hierarchical Insurance Claims Modeling
Hierarchical Insurance Claims Modeling
复制标题
DOI：
10.1198/016214508000000823
复制
发表时间：
2008-12-01
影响因子：
3.7
通讯作者：
Valdez, Emiliano A.
中科院分区：
文献类型：
--
作者：
Frees, Edward W.;Valdez, Emiliano A.
本文详细介绍了统计建模的工作。微观层面的汽车保险记录。我们认为1993-2001年的数据来自新加坡的主要保险公司。详细的微观记录。我们指的是在单个车辆层面上的经验，包括车辆和驾驶员的特征、保险范围和索赔经验。按年份索赔经验包括保险索赔类型的详细信息，例如索赔是否是由于第三方受伤、第三方财产损失或被保险人损失索赔。以及相应的索赔金额。我们提出了一个分层模型的三个组成部分。对应于频率。类型.和索赔的严重性。第一个模型是评估索赔频率的负二项回归模型。驾驶员的性别、年龄、无索赔折扣、车辆年龄和类型是预测索赔事件的重要变量。第二种是多项logit模型，预测保险索赔的类型，是否为第三者伤害、第三者财产损失。被保险人自身的损害或一些组合年车龄。和车辆类型是该分量的重要预测因子。我们的第三个模型用于严重性组件。在这里，我们使用第二种长尾分布的广义beta来计算索赔额，并将预测变量也纳入其中。年车龄和人的年龄是这一组成部分的重要预测因素。一点也不奇怪。我们发现它在不同的索赔类型之间存在显著的依赖性，我们使用t-copula来解释这种依赖性。三要素模型为评估评级变量的重要性提供了依据。当我们把它们放在一起的时候。与传统方法相比，集成模型可以更有效地预测汽车索赔。使用模拟。我们证明了这一点，通过开发预测分布和计算保费的替代覆盖范围的限制。
This work describes statistical modeling of detailed. microlevel automobile insurance records. We consider 1993-2001 data a from it major insurance company in Singapore. By detailed microlevel records. we mean experience at the individual vehicle level, including vehicle and driver characteristics, insurance coverage, and claims experience. by year. The claims experience consists of detailed information oil the type of insurance claim such as whether the claim is due to injury to a third party, property damage to it third party, or claims for damage to the insured. as well its the corresponding claim amount. We propose a hierarchical model for three components. corresponding to the frequency. type. and severity of claims. The first model is it negative binomial regression model for assessing claim frequency. The driver's gender, age, and no claims discount, its well as vehicle age and type, turn out to be important variables for predicting the event of a claim. The second is a multinomial logit model to predict the type of insurance claim, whether it is third-party injury, third-party property damage. insured's own damage or some combination year vehicle age. and vehicle type turn out to be important predictors for this component. Our third model is for the severity component. Here we use a generalized beta of the second kind of long-tailed distribution for claim amounts and also incorporate predictor variables. Year. vehicle age, and person's age turn Out to be important predictors for this component. Not Surprisingly. we show it significant dependence among the different claim types we use a t-copula to account for this dependence. The three-component model provides justification for assessing the importance of it rating variable. When taken together. the integrated model allows more efficient prediction of automobile claims compared with than traditional methods. Using Simulation. we demonstrate this by developing predictive distributions and calculating premiums under alternative coverage limitations.