Scholarlink

<p>Accurate forecasting of agricultural commodity prices is crucial for maintaining market stability, effective risk management, and informed decision-making, particularly in developing economies with high price volatility and heterogeneous market structures. Traditional statistical models and recurrent deep learning approaches often struggle to capture nonlinear dynamics, abrupt fluctuations, and long-range temporal dependencies in agricultural price series. To overcome these limitations, this study proposes a CNN-Transformer hybrid architecture that combines the local feature extraction of Convolutional Neural Networks (CNNs) with the global dependency modelling of Transformer self-attention mechanisms, specifically designed to address limitations of existing hybrid models such as sequential bottlenecks, vanishing gradients, and limited scalability. The framework is evaluated on weekly potato prices from four structurally diverse Indian markets-Azadpur, Ludhiana, Dehradun, and Farrukhabad, covering varying data lengths and volatility regimes. Systematic hyperparameter tuning and extensive experiments demonstrate that the CNN-Transformer consistently outperforms established benchmarks, including CNN, LSTM, Bi-LSTM, GRU, CNN-LSTM, and standalone Transformer models, across RMSE, MAE, and MAPE metrics.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CNN-transformer hybrid deep learning model for agricultural commodities price forecasting

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月8日

查看全文
  • B. S. Varshini,
  • Md Wasi Alam,
  • G. H. Harish Nayak,
  • G. Avinash,
  • Vinayaka,
  • Rajeev Ranjan Kumar,
  • Mrinmoy Ray

摘要

Accurate forecasting of agricultural commodity prices is crucial for maintaining market stability, effective risk management, and informed decision-making, particularly in developing economies with high price volatility and heterogeneous market structures. Traditional statistical models and recurrent deep learning approaches often struggle to capture nonlinear dynamics, abrupt fluctuations, and long-range temporal dependencies in agricultural price series. To overcome these limitations, this study proposes a CNN-Transformer hybrid architecture that combines the local feature extraction of Convolutional Neural Networks (CNNs) with the global dependency modelling of Transformer self-attention mechanisms, specifically designed to address limitations of existing hybrid models such as sequential bottlenecks, vanishing gradients, and limited scalability. The framework is evaluated on weekly potato prices from four structurally diverse Indian markets-Azadpur, Ludhiana, Dehradun, and Farrukhabad, covering varying data lengths and volatility regimes. Systematic hyperparameter tuning and extensive experiments demonstrate that the CNN-Transformer consistently outperforms established benchmarks, including CNN, LSTM, Bi-LSTM, GRU, CNN-LSTM, and standalone Transformer models, across RMSE, MAE, and MAPE metrics.