Price fluctuations in agricultural commodities have a negative impact on the country’s GDP. Price prediction assists the agricultural supply chain in making necessary decisions to minimize and manage the risk of price fluctuations. Although traditional models for forecasting, such as ARIMA and exponential smoothing, are widely used, it is difficult to predict price fluctuations accurately, especially when dealing with large amounts of data. To overcome this lacuna, various machine learning and deep learning models have recently been used to forecast price series. To be precise, the most significant finding is that deep learning models are suitable for predicting commodity prices.

Highlights

• RNNs have been applied for forecasting time series data in most scientific and industrial fields, but mainly in commodity price forecasting.
• RNNs, such as the gated recurrent unit, LSTM neural network, and improvement models, can be powerful prediction alternatives to traditional neural networks and can obtain better prediction results.