THE PREDICTION OF TIME-DEPENDENT CLAIMS FREQUENCY OF HEALTH INSURANCE: RANDOM EFFECT AND INTEGER-VALUED AUTOREGRESSIVE(1) MODELS

• Main Author: Tesalonika Riwie W., Maria
• Format: Final Project
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/55193
• Institution: Institut Teknologi Bandung

In a general insurance business, the claims frequency is an essential part in calculating the risk of financial losses. In this Final Project, the expected future claims frequency is determined using a panel data of inpatient health insurance claims for underwriting years 2015, 2016, 2017, 2018, and 2019 of a general insurance company. The claims frequency is modeled using the characteristics of the policyholders, such as: gender; age; and types of diseases; and using the time-dependent Poisson and Negative Binomial probability distributions which model the interdependence of the data between underwriting years. In this study, the predictions obtained by the Random Effect model, which is a model using the Bayesian approach in calculating the prediction of the claims frequency, are compared with those obtained using the Integer-valued Autoregressive(1) or INAR-1 model, which uses the Markovian properties in determining the predictions. The parameter estimates are obtained using the Maximum Likelihood Estimation method; and the Wald’s test is used to determine which parameters are significant. The AIC and BIC values are used to determine the best model from several resulted regression models. For the historical data used, based on the obtained AIC and BIC values, it is found that the Random Effect model is the best model in predicting the claims frequency