The model of life insurance claims with actuarial smoothing approach by using GLM Poisson regression

Many statistical models are used in the actuarial calculation process in modeling insurance data, one of which is the Generalized Linear Model (GLM). This study will estimate the actuarial approach of the value of the claims in the multinomial setting with the GLM Poisson Regression model. The data used in this study is the value of life insurance claims with Poisson distribution at West Sumatra Province as many as 1021 data. The best model is selected by comparing the smallest Akaike's Information Criterion (AIC) value, with significant risk factor parameters such as contract, age, month, and benefit. The smoothing approach is due to the best model of GLM Poisson Regression. The average claim value of the best GLM Poisson Regression model is lying in the second category between 20 million until 40 million rupiah. It is mean with the increase of the value of the claims on insurance indicates the high awareness of the public about the importance of insurance.