Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Engineering Science Letter
Manurung, Zoni Zikro
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Forecasting Rice Price Volatility Utilizing BiLSTM-SHAP to Ensure National Food Stability Manurung, Juliana Damayanti; Sikana, Nadya; Simamora, Fandi Presly; Manurung, Zoni Zikro
Engineering Science Letter Vol. 4 No. 03 (2025): Engineering Science Letter
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/IISTR.esl.001360

Abstract

Rice price volatility in Indonesia remains a persistent economic issue, partly driven by climate variability and fluctuations in national rice production, prompting the government to resort to substantial annual imports. However, the extent to which domestic production factors and weather conditions influence future rice prices has not been quantitatively evaluated. This study aims to forecast short-term rice prices in Indonesia by integrating multiple time-series features, including rice prices, harvested area, paddy production, and weather features, using a Bidirectional Long Short-Term Memory (BiLSTM) network. Daily data from 2013 to 2024 were collected from the National Statistics Agency, Food Price Panel, and the Meteorology and Climatology Agency. Chronological split was applied for training, validation, and testing to preserve temporal dependency. The optimal model predicts rice prices seven days ahead using 256 hidden units, achieving MAE of 128.84 IDR, RMSE of 157.98 IDR, and R² of 0.694. SHAP analysis shows that historical rice prices have the strongest contribution with a SHAP value of 0.969652, significantly higher compared to other features. The results demonstrate that integrating agricultural and climatic inputs improves predictive performance while providing interpretable insights into price-forming factors.
Co-Authors Fandi Presly Simamora Manurung, Juliana Damayanti Nadya Sikana