Rice Price Prediction with Long Short-Term Memory (LSTM) Neural Network

Rice Price Prediction with Long Short-Term Memory (LSTM) Neural Network

prediction; variability; long short-term memory; artificial neural networks

Rice is a crucial commodity, especially in countries that rely on rice as a staple food. Fluctuations in rice prices can impact inflation, purchasing power, and economic stability. Therefore, an effective method for forecasting rice prices is essential for timely decision-making. This study aims to develop a rice price forecasting model by incorporating weather variability. Using Long Short-Term Memory (LSTM) neural networks, the model is expected to provide accurate predictions and guide decision-making in rice trading. LSTM is effective in analyzing time-series data. In this study, LSTM was used to examine the relationship between weather variability, crop yields, and land area with rice prices. Daily data from 2015 to 2023 were collected to build a model capable of predicting future rice prices. The results showed that the LSTM model achieved a Root Mean Squared Error (RMSE) of 0.054, indicating high prediction accuracy. This model allows stakeholders, including farmers, traders, and government officials, to better understand future rice price movements. This, in turn, helps them implement more effective strategies in managing rice supply and stabilizing prices

Rahmat Hidayat1*, Irawan Wibisonya

https://jurnal.iaii.or.id/index.php/RESTI/article/view/6041/978

Computer Science, Sains and Technology, Universitas Putra Bangsa, Kebumen, Indonesia

23-10-2024

FAJAR BAGUS W

PDF

ENGLISH

TEXT