Search

Crude oil is a vital natural resource needed worldwide and the most demanded commodity. Fluctuating oil prices can affect a country's economic conditions e.g., economic growth, inflation rate, money supply, exchange rate and interest rates. Consequently, statistical forecasting methods are needed for a more accurate prediction in period t to support decision-making. This study aims to predict crude oil prices during the Covid-19 pandemic and compare the performance of crude oil price forecasting using the Fuzzy Time Series (FTS) Markov Chain method and Autoregressive Integrated Moving Average (ARIMA) method. The data used is daily crude oil prices with West Texas Intermediate (WTI) Standard in US$/barrel from March 3, 2020, to March 31, 2022. Forecasting with the FTS Markov Chain method resulted in a mean absolute percentage error (MAPE) of 2.76%, and root mean square error (RMSE) of 580.3. The best model for ARIMA is ARIMA (0,1,1) which produces MAPE of 3.85% and RMSE 856.7. Due to the MAPE & RMSE values in the FTS Markov Chain method being smaller than the ARIMA method. Hence, forecasting using the FTS Markov Chain has better performance than the ARIMA method in the forecasting of crude oil prices during the Covid-19 pandemic. [ABSTRACT FROM AUTHOR]