Modeling and Forecasting of COVID-19 Confirmed Cases in Indonesia Using ARIMA and Exponential Smoothing
Hedi, M.V. Joyce Merawati BR · Proceedings of the International Seminar of Science and Applied Technology (ISSAT 2020) · 2020
The number of confirmed COVID -19 cases in Indonesia is increasing rapidly.Therefore forecasting of the number of confirmed cases in the future needs to be predicted, so that the government can prepare to handle this pandemic case.The purpose of this study is to provide information on the estimated number of COVID -19 cases in the future in Indonesia.The data used are daily time series data, the number of confirmed cases of COVID-19 from March to August 2020.This study applies two mathematical models, namely: ARIMA and exponential smoothing.Based on ARIMA model, the parameter equations of the ARIMA model (0,2,1), (1,2,0), and (1,2,1) are obtained.The calculation results of Akaike's Information Criterion (AIC) and Schwartsz Bayesian Criterion (SBC), ARIMA (1,2,1) is the most suitable model.The exponential smoothing model, the model with the smallest root mean square error (RMSE) is obtained namely the exponential smoothing model involving trends.The results of the RMSE calculation of the two models, the ARIMA (1,2,1) model is the most suitable forecast the number of COVID -19 cases in Indonesia.