Development of rental property insurance models with Generalized Linear Models (GLM)

Abstract

In this paper we developed insurance model on property rental business using. Generalized Linear Models (GLM). GLM was chosen because the data on property rental match with the characteristics of GLM. Analysis of the model is done by looking at the relationship between the distribution functions that are most widely used in the analysis of property rental data. The models for the relations of distribution functions are: Poisson-Gamma, Poisson-Inverse Gauss, Negative Binomial-Gamma and Negative Binomial-Inverse Gauss. The relationship between the distributions is seen from the root-mean-squared error (RMSE) and absolute mean error (MAE). The simulation results show that the model formed in the case of random effects increases in standard deviation values also increases the variation value on the average estimator. This is in accordance with the condition that the addition of standard deviation means that there is an increase in the variance of the data.