Estimating Territory Risk Relativity Using Generalized Linear Mixed Models and Fuzzy C-Means Clustering
Open Access
Abstract
Territory risk analysis has played an important role in auto insurance rate regulation. It aims to design rating territories from a set of basic rating units so that their respective risk relativities can be estimated to reflect the regional risk of insurance. In this work, spatially constrained clustering is first applied to insurance loss data to form such regions, using the forward sortation area (FSA) as a basic rating unit. The groupings of FSA by spatially constrained clustering reduce the insurance rate heterogeneity caused by smaller risk exposures. Furthermore, the generalized linear mixed model (GLMM) is proposed to derive the risk relativities of clusters and each FSA. In addition, as an alternative approach, fuzzy C-Means clustering is proposed to derive the risk relativity of FSA, and the obtained results are compared to the ones from GLMM. The spatially constrained clustering and risk relativity estimation help to retrieve a set of territory risk benchmarks used in rate filings within the regulation process. It also provides guidance for auto insurance companies on rate making.Keywords
This publication has 32 references indexed in Scilit:
- Evaluation of forest fire risk using the Apriori algorithm and fuzzy c-means clusteringJournal of Forest Science, 2017
- Customer Clustering Using a Combination of Fuzzy C-Means and Genetic AlgorithmsInternational Journal of Business and Management, 2016
- Auto insurance fraud detection using unsupervised spectral ranking for anomalyThe Journal of Finance and Data Science, 2016
- Auto Insurance Premium Calculation Using Generalized Linear ModelsProcedia Economics and Finance, 2015
- Generalized Linear Models in Vehicle InsuranceActa Universitatis Agriculturae et Silviculturae Mendelianae Brunensis, 2014
- Bankruptcy forecasting: A hybrid approach using Fuzzy c-means clustering and Multivariate Adaptive Regression Splines (MARS)Expert Systems with Applications, 2011
- Zip codes and spatial analysis: Problems and prospectsSocio-Economic Planning Sciences, 2008
- Generalized linear mixed models: a review and some extensionsLifetime Data Analysis, 2007
- Actuarial statistics with generalized linear mixed modelsInsurance: Mathematics and Economics, 2007
- Modelling repeated insurance claim frequency data using the generalized linear mixed modelJournal of Applied Statistics, 2003