Answers are grounded in this paper and cite their sources.
Innovative approach improves agricultural price forecasting accuracy, indicating its effectiveness across multiple commodities.
Agricultural product price forecasting plays a crucial role in ensuring food security, stabilizing markets, and supporting informed policymaking. However, the inherent volatility and nonlinearity of agricultural price movements pose significant challenges for accurate prediction. This study presents an innovative approach that integrates Variational Mode Decomposition (VMD) and Multivariate VMD (MVMD) with a Deep Temporal Convolutional Network (Deep-TCN), enabling more accurate and stable forecasts through a two-stage decomposition process. Empirical evaluations across multiple commodities — including soybean meal, soybean, and corn — demonstrate that the proposed model consistently outperforms ten benchmark methods across short- and long-term horizons. For example, it achieves MAPE values as low as 0.0103 (soybean meal), 0.0111 (soybean), and 0.0055 (corn) for one-day-ahead predictions, with substantial improvements over traditional deep learning and machine learning models. These results confirm the model’s effectiveness in capturing both short-term volatility and long-term trends, and highlight its strong generalizability across different agricultural markets. • A novel approach combines VMD, MVMD, and Deep-TCN for price forecasting. • Secondary decomposition enhances prediction accuracy of agricultural prices. • Deep-TCN captures both short-term and long-term dependencies in time series. • The proposed method outperforms traditional models across multiple horizons.
No takes yet. Share an insight, caveat, or question.
Yu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: