An integrated framework for multi-commodity agricultural price forecasting and anomaly detection using attention-boosted models
Global agricultural systems are increasingly exposed to price instability driven by climate extremes, logistic disruptions, and market uncertainty. These conditions complicate efforts to monitor and manage price behaviours in essential commodity markets. Micro, small, and medium enterprises (MSMEs),...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-08-01
|
| Series: | Journal of Agriculture and Food Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666154325003928 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849417781974401024 |
|---|---|
| author | Eko Sediyono Kristoko Dwi Hartomo Christian Arthur Intiyas Utami Ronny Prabowo Raymond Chiong |
| author_facet | Eko Sediyono Kristoko Dwi Hartomo Christian Arthur Intiyas Utami Ronny Prabowo Raymond Chiong |
| author_sort | Eko Sediyono |
| collection | DOAJ |
| description | Global agricultural systems are increasingly exposed to price instability driven by climate extremes, logistic disruptions, and market uncertainty. These conditions complicate efforts to monitor and manage price behaviours in essential commodity markets. Micro, small, and medium enterprises (MSMEs), which operate with constrained resources and limited access to data-driven tools, are particularly susceptible to sudden and irregular price shifts. Their ability to maintain stable operations depends on timely identification of market anomalies and reliable planning information. This underscores the importance of accurate price forecasting, yet deep learning models such as Bidirectional Long Short-Term Memory (LSTM) and the Gated Recurrent Unit often struggle to capture long-term dependencies and detect irregular price behaviors. To bridge the gap, this study proposes a deep learning framework that integrates Transformer models for price prediction and an attention-boosted LSTM Variational Autoencoder (VAE) for anomaly detection. Using daily price data collected from the period of January 2020 to mid-June 2024, this study demonstrated that Transformers outperformed traditional models while accurately capturing market trends and sudden fluctuations. Additionally, the attention-boosted anomaly detection model can outperform standard LSTM and artificial neural network-VAEs in identifying unexpected price changes. The proposed models outperformed baseline methods by achieving lower forecasting and anomaly detection errors. By addressing critical limitations in existing forecasting approaches, specifically their inability to capture abrupt anomalies, this study provides essential support for enhancing MSMEs’ resilience and improving decision-making under volatile market conditions. |
| format | Article |
| id | doaj-art-9c6aeedc77db47229805e6bfce0d369d |
| institution | Kabale University |
| issn | 2666-1543 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Agriculture and Food Research |
| spelling | doaj-art-9c6aeedc77db47229805e6bfce0d369d2025-08-20T03:32:37ZengElsevierJournal of Agriculture and Food Research2666-15432025-08-012210202110.1016/j.jafr.2025.102021An integrated framework for multi-commodity agricultural price forecasting and anomaly detection using attention-boosted modelsEko Sediyono0Kristoko Dwi Hartomo1Christian Arthur2Intiyas Utami3Ronny Prabowo4Raymond Chiong5Faculty of Information Technology, Satya Wacana Christian University, Salatiga, IndonesiaFaculty of Information Technology, Satya Wacana Christian University, Salatiga, IndonesiaSchool of Transdisciplinary, University of Technology Sydney, Ultimo, NSW 2007, AustraliaFaculty of Economic and Business, Satya Wacana Christian University, Salatiga, IndonesiaFaculty of Economic and Business, Satya Wacana Christian University, Salatiga, IndonesiaSchool of Science and Technology, University of New England, Parramatta, NSW 2150, Australia; School of Information and Physical Sciences, University of Newcastle, Callaghan, NSW 2308, Australia; Corresponding author. School of Science and Technology, University of New England, Parramatta, NSW 2150, Australia.Global agricultural systems are increasingly exposed to price instability driven by climate extremes, logistic disruptions, and market uncertainty. These conditions complicate efforts to monitor and manage price behaviours in essential commodity markets. Micro, small, and medium enterprises (MSMEs), which operate with constrained resources and limited access to data-driven tools, are particularly susceptible to sudden and irregular price shifts. Their ability to maintain stable operations depends on timely identification of market anomalies and reliable planning information. This underscores the importance of accurate price forecasting, yet deep learning models such as Bidirectional Long Short-Term Memory (LSTM) and the Gated Recurrent Unit often struggle to capture long-term dependencies and detect irregular price behaviors. To bridge the gap, this study proposes a deep learning framework that integrates Transformer models for price prediction and an attention-boosted LSTM Variational Autoencoder (VAE) for anomaly detection. Using daily price data collected from the period of January 2020 to mid-June 2024, this study demonstrated that Transformers outperformed traditional models while accurately capturing market trends and sudden fluctuations. Additionally, the attention-boosted anomaly detection model can outperform standard LSTM and artificial neural network-VAEs in identifying unexpected price changes. The proposed models outperformed baseline methods by achieving lower forecasting and anomaly detection errors. By addressing critical limitations in existing forecasting approaches, specifically their inability to capture abrupt anomalies, this study provides essential support for enhancing MSMEs’ resilience and improving decision-making under volatile market conditions.http://www.sciencedirect.com/science/article/pii/S2666154325003928Agricultural commodityPrice forecastingTransformerLSTM-VAEAnomaly detectionAttention mechanism |
| spellingShingle | Eko Sediyono Kristoko Dwi Hartomo Christian Arthur Intiyas Utami Ronny Prabowo Raymond Chiong An integrated framework for multi-commodity agricultural price forecasting and anomaly detection using attention-boosted models Journal of Agriculture and Food Research Agricultural commodity Price forecasting Transformer LSTM-VAE Anomaly detection Attention mechanism |
| title | An integrated framework for multi-commodity agricultural price forecasting and anomaly detection using attention-boosted models |
| title_full | An integrated framework for multi-commodity agricultural price forecasting and anomaly detection using attention-boosted models |
| title_fullStr | An integrated framework for multi-commodity agricultural price forecasting and anomaly detection using attention-boosted models |
| title_full_unstemmed | An integrated framework for multi-commodity agricultural price forecasting and anomaly detection using attention-boosted models |
| title_short | An integrated framework for multi-commodity agricultural price forecasting and anomaly detection using attention-boosted models |
| title_sort | integrated framework for multi commodity agricultural price forecasting and anomaly detection using attention boosted models |
| topic | Agricultural commodity Price forecasting Transformer LSTM-VAE Anomaly detection Attention mechanism |
| url | http://www.sciencedirect.com/science/article/pii/S2666154325003928 |
| work_keys_str_mv | AT ekosediyono anintegratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT kristokodwihartomo anintegratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT christianarthur anintegratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT intiyasutami anintegratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT ronnyprabowo anintegratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT raymondchiong anintegratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT ekosediyono integratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT kristokodwihartomo integratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT christianarthur integratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT intiyasutami integratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT ronnyprabowo integratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels AT raymondchiong integratedframeworkformulticommodityagriculturalpriceforecastingandanomalydetectionusingattentionboostedmodels |