EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Rice Price Prediction In East Java Based on Weather Using Long Short-Term Memory (LSTM)

Davina Mufidah, Noviyanti Santoso, Moch. Abdillah Nafis

Journal of Applied Informatics and Computing · 17.04.2026 · 10 (2) · 1561-1567

DOI: 10.30871/jaic.v10i2.12515 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Informatics and Computing, online erschienen am 17.04.2026. Verfasst von Davina Mufidah und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rice is the primary staple food commodity in Indonesia, crucial for food security and economic stability, with price fluctuations significantly affecting public purchasing power. Data from Statistics Indonesia (BPS) in May 2025 indicated a 0.15% decline in medium-quality rice prices in East Java; however, price disparities between regions remain high, necessitating accurate prediction models. East Java, as one of the major production hubs contributing 20% to the national paddy production, is vulnerable to climate change phenomena such as El Niño and La Niña, which impact harvests and prices. Rice price fluctuations are influenced by various complex factors, including non-linear weather conditions such as rainfall, temperature, and humidity. This study focuses on forecasting the price of medium-quality rice, the most widely consumed variety in Indonesia. The multivariate Long Short-Term Memory (LSTM) model is proposed due to its capability in handling long-term dependencies and non-linear patterns within time-series data. This study analyzes the performance of LSTM using historical rice price data and integrates weather factors to enhance prediction accuracy. Daily data from January 1, 2020, to December 31, 2025, was utilized, sourced from the National Strategic Food Price Information Center (PIHPS) and BMKG East Java, covering variables such as medium rice price, rainfall, wind speed, humidity, sunshine duration, and temperature. The results indicate that the LSTM model with a configuration of 45 timesteps, a dropout rate of 0.3, a batch size of 16, 150 neurons, and 150 epochs yielded the most optimal performance, achieving a Train MAPE of 0.73% and a Test MAPE of 1.40%. These findings empirically demonstrate that a historical memory of approximately 1.5 months plays a crucial role in prediction accuracy, perfectly aligning with the short-to-medium-term supply chain dynamics. Based on the out-of-sample forecasting results for January to March 2026, the model predicts a sharp price correction in early January, followed by a gradual increase that stabilizes in the range of Rp14,380–Rp14,400 per kilogram. This projection visualizes a new equilibrium, confirming that historical climate damage establishes a permanent baseline price shift, while the high forecast accuracy (MAPE 0.25%) provides a highly reliable basis for government policy formulation.

Zitieren

APA

Mufidah, D., Santoso, N., & Nafis, M. A. (2026). Rice Price Prediction In East Java Based on Weather Using Long Short-Term Memory (LSTM). Journal of Applied Informatics and Computing, 10(2), 1561-1567. https://doi.org/10.30871/jaic.v10i2.12515

Vancouver

Mufidah D, Santoso N, Nafis MA. Rice Price Prediction In East Java Based on Weather Using Long Short-Term Memory (LSTM). Journal of Applied Informatics and Computing. 2026;10(2):1561-1567. doi:10.30871/jaic.v10i2.12515

BibTeX
@article{Mufidah2026,
  author = {Mufidah, Davina and Santoso, Noviyanti and Nafis, Moch. Abdillah},
  title = {Rice Price Prediction In East Java Based on Weather Using Long Short-Term Memory (LSTM)},
  journal = {Journal of Applied Informatics and Computing},
  year = {2026},
  volume = {10},
  number = {2},
  pages = {1561--1567},
  doi = {10.30871/jaic.v10i2.12515}
}
Kostenlos starten →