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),...

Full description

Saved in:
Bibliographic Details
Main Authors: Eko Sediyono, Kristoko Dwi Hartomo, Christian Arthur, Intiyas Utami, Ronny Prabowo, Raymond Chiong
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