By H. Guo, D. Zhang, S. Liu📧, Lei Wang📧, and Y. Ding
In Decision Support Systems, 2021, 151:113650. https://doi.org/10.1016/j.dss.2021.113650
Cryptocurrency price forecasting plays an important role in financial markets. Traditional approaches face two challenges: (1) it is difficult to ascertain the influential factors related to price forecasting; and (2) due to the 24/7 trading policy, cryptocurrencies’ prices face very large fluctuations, thus weakening the forecasting power of traditional models. To address these issues, we focus on Bitcoin and identify the influential factors related to its price forecasting from the perspective of underlying blockchain transactions. We then propose a price forecasting model WT-CATCN, which leverages Wavelet Transform (WT) and Casual Multi-Head Attention (CA) Temporal Convolutional Network (TCN), to forecast cryptocurrency prices. Our model can capture important positions of input sequences and model the correlations among different data features. Using real-world Bitcoin trading data, we test and compare WT-CATCN with other state-of-the-art price forecasting models. The experiment results show that our model improves the price forecasting performance by 25%.
Keywords: Cryptocurrency; Blockchain; Bitcoin; Price forecasting; Deep learning
Metals markets have experienced increases in price changes not only in frequency, but also in magnitude, with prices and spreads continuing to move in unpredictable directions. Notable volatility can be observed in prices of copper, steel, and aluminum (the most commonly used nonferrous metal and the second-most commonly used metal after iron). Price volatility posts challenges for industrial buyers of metal raw materials on multiple fronts—ranging from the procurement professionals buying materials, the logistics and transportation personnel moving the materials, the finance department forecasting and managing expenses, and the sales and marketing staff struggling to pass unanticipated cost increases on to customers. The unrelenting metal price volatility, the wider uses of hedging strategies as a mitigation approach, along with the increasing convolutions of hedging processes, governance, and technological requirements provide a fundamental premise of this paper. Focusing on aluminum, copper, silver, and steel (cold rolled and hot rolled) markets, the paper identifies and catalogues metal-capable market intelligence and decision-support tools, and explores hedge program characteristics and strategies employed by industrial buyers in mitigating price fluctuation.