文章基本信息

标题：Predictive Modeling of Multi-Peril Homewoners Insurance
本地全文：下载
作者：Edward W. (Jed) Frees ; Glenn Meyers, FCAS ; A. David Cummings, FCAS 等
期刊名称：Casualty Actuarial Society Forum
印刷版ISSN：1046-6487
出版年度：2011
卷号：2
出版社：CAS
摘要：Predictive models are used by insurers for underwriting and ratemaking in personal lines insurance. Focusing on homeowners insurance, this paper provides a systematic comparison of many predictive generalized linear models. We compare pure premium (Tweedie) and frequency/severity models based on single perils as well as multiple perils. With multiple perils, we also introduce instrumental variable models that account for dependencies among perils. We calibrate these models using a database of detailed individual policyholder experience. To evaluate these many alternatives, we emphasize out-of-sample model comparisons. We show how to use Gini indices for economic validation. We also consider a nonparametric regression that is used extensively by the statistical learning community. We find that different validation measures can help the actuary critically evaluate the effectiveness of alternative scoring procedures.