Forecasting Model of Export and Import Value of Oil and Gas Using Gated Recurrent Unit Method

Abstract

Indonesia’s natural resources are abundant, including oil and gas. It is one of the countries active in international trade, including exports and imports. Oil and gas exports are a significant source of income for the country, encouraging economic growth. Oil and gas imports are very important to meet domestic energy needs, which continue to increase in demand. Increasing oil and gas imports can increase the trade balance, which can affect the country’s economic stability if the value of imports exceeds the value of exports. Forecasting is a solution to overcome these problems by forecasting the value of oil and gas exports and imports. The gated recurrent unit (GRU) method is used for forecasting in this study because it has a simple computation and fairly high accuracy. The dataset used is monthly time series data from 1993 to 2023 from the website of the Badan Pusat Statistik (BPS). The MAPE results on the GRU model forecast the value of oil and gas exports and imports at 12.19% and 14.30%, respectively. The best average forecasting of export and import values obtained a MAPE of 13.38%.

Keywords

• forecasting model
• oil and gas import export value
• deep learning
• gated recurrent unit model