Rice is a staple food commodity in Indonesia, including in Padang City, which is only able to meet 30% of its rice needs locally. Fluctuations in rice price affect economic stability and public purchasing power, making rice price prediction important. This study aims to develop a rice price prediction model using the Gated Recurrent Unit(GRU) method, utilizing actual historical rice price data from 2022 to April 2025 obtained from the PIPHS Nasional. The dataset includes three type of rice based on quality. Namely Bawah I, Medium I, and Super I. the result show that the GRU model provides the best model evaluation based on three types of rice, with a MAPE of 0, 49% for Medium I quality rice and an RMSE of 0,0587 for super I rice. And the highest MAPE was found in Super I quality rice, namely 4,41% , an RMSE value of 1,222 for Lower I quality rice. This model can be used to assist decision making related to rice price stability, particularly in Padang City, which relies on supplies from other regions. Overall, GRU proves effective in forecasting rice price supporting policies for more stable prices.
Copyrights © 2025