Motorized vehicles are one of the means of transportation used by Indonesian people. As of 2021, the Central Statistics Agency (BPS) recorded the growth of motorized vehicles in Indonesia reaching 141,992,573 vehicles. Lack of control over the number of motorized vehicles results in losses for various parties, such as accidents, damage and other unwanted losses. The size of insurance claims has the potential to fluctuate, because it is influenced by several factors, such as policy changes, market conditions and economic conditions. This research aims to predict the size of motor vehicle insurance claims using the ARMA-GARCH model which is used to predict the size of vehicle insurance claims by dealing with non-stationarity and heteroscedasticity in time series data. Based on research, the best model obtained is the ARMA(3,3)-GARCH(1,0) model which produces nine significant parameters. Meanwhile, based on the MAPE value, it shows that the ARMA(3,3)-GARCH(1,0) model is quite accurate. The results of this research can be taken into consideration in predicting the size of insurance claims in the future.
Keywords
Prediction, insurance claim, motor vehicle, ARMA-GARCH
Bollerslev, T. (1986). Generalzed Autoregressive Conditional Heteroscedasticity. Journal of Econometrics, 31(3), 307–327.
Engle, R. F. (1982). Autoregressive conditional heteroskedasticity twith estimates of thevariance of United Kingdom Inflation. Econometrica, 50(4), 987-1008.
E.P.Box, G. et al. (2015). Time Series Analysis: Forecasting and Control. 5th Edition. New Jersey: Wiley.
Hartati, H. (2017). Penggunaan Metode ARIMA dalam Meramal Pergerakan Inflasi’. Jurnal Matematika Sains Dan Teknologi, 18(1), 1–10.
Montgomery, D.C., Jennings, C. L., dan Kulachi, M. (2008). Introduction to Time Series Analysis and Forecasting. New Jersey: John Wiley & Sons. Inc.
Wei, W.W.S. (2006). Time Series Analysis: Univariate and Multivariate Methods. New York: Pearson.
Creation is distributed below Lisensi Creative Commons Atribusi 4.0 Internasional.