Hybrid empirical mode decomposition-ARIMA for forecasting price of rice

The prices of rice keep changing from time to time. It creates risks to producers, suppliers, consumers, and other parties that involved in marketing and production of rice. Thus, it is important to do forecasting on rice prices data set. This paper tries to apply a hybrid methodology which is an integration of empirical mode decomposition (EMD) and autoregressive integrated moving average (ARIMA). The EMD-ARIMA is applied on the data of the monthly prices of rice in Malaysian Ringgit (MYR) per metric ton. Forecasting result found that EMD can improve the accuracy of the ARIMA forecasting on the prices of rice based on the comparison of root mean squared error (RMSE) and mean absolute error (MAE).