Iron Ore Price Forecast based on a Multi-Echelon Tandem Learning Model

Abstract

Iron ore has had a highly global market since setting a new pricing mechanism in 2008. With current dollar values, iron ore concentrate for sale price, which was $39 per tonne (62% Fe) in December 2015, reached $218 per tonne (62% Fe) in mid-2021. It is hovering around $120 in October 2023 (cf. https://tradingeconomics.com/commodity/iron-ore). The uncertainty associated with these fluctuations creates hardship for iron ore mine operators and steelmakers in planning mine development and making future sale agreements. Therefore, iron ore price forecasting is of special importance. This paper proposes a cutting-edge multi-echelon tandem learning (METL) model to forecast iron ore prices. This model comprises variational mode decomposition (VMD), multi-head convolutional neural network (MCNN), stacked long short-term-memory (SLSTM) network, and attention mechanism (AT). In the proposed METL (i.e., the combination of VMD, MCNN, SLSTM, AT) model, the VMD decomposes the time series data into sub-sequential modes for better measuring volatility. Then, the MCNN is applied as an encoder to extract spatial features from the decomposed sub-sequential modes. The SLSTM network is adopted as a decoder to extract temporal features. Finally, the AT is employed to capture spatial–temporal features to obtain the complete forecasting process. Extensive computational experiments are conducted based on daily-based and weekly-based iron ore price datasets with different time scales. It was validated that the proposed METL model outperformed its single-echelon and other categorized models by 10–65% in range. The proposed METL model can improve the prediction accuracy of iron ore prices and thus help mining and steelmaking enterprises to determine their sale or purchase strategies.