What question did this study set out to answer?

To develop a model for more accurate forecasting of agricultural product prices using advanced decomposition techniques.

Forecasting fluctuations in agricultural markets: The power of secondary decomposition and neural networks

View Full Paper

Ask AI

Bookmark

Authors

Innovative approach improves agricultural price forecasting accuracy, indicating its effectiveness across multiple commodities.

To develop a model for more accurate forecasting of agricultural product prices using advanced decomposition techniques.
Integrated Variational Mode Decomposition (VMD) and Multivariate VMD (MVMD) with Deep Temporal Convolutional Network (Deep-TCN).
Conducted empirical evaluations on commodities like soybean meal, soybean, and corn.
Assessed performance against ten benchmark forecasting methods.
Calculated Mean Absolute Percentage Error (MAPE) for predictions.
Achieved MAPE values as low as 0.0103 for soybean meal, 0.0111 for soybean, and 0.0055 for corn.
Demonstrated consistent performance improvements over traditional deep learning and machine learning models.
Showed effectiveness in capturing short-term volatility and long-term trends across agricultural markets.

Yu et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark