TY - JOUR
T1 - Bitcoin price forecasting
T2 - A perspective of underlying blockchain transactions
AU - Guo, Haizhou
AU - Zhang, Dian
AU - Liu, Siyuan
AU - Wang, Lei
AU - Ding, Ye
N1 - Funding Information:
Dian Zhang received the PhD degree in computer science and engineering from the Hong Kong University of Science and Technology (HKUST), Hong Kong, in 2010. She is currently an associate professor at Shenzhen University. Her research interests include big data analytics and mobile computing. She has published many papers in top tier journals including IEEE Transaction on Parallel Computing, Transaction on Mobile Computing. She is the PI of many projects including National Natural Science Foundation of China (NSFC). She received 2nd Class Academic Research Outstanding Award in Nature Science from the Ministry of Education of China in 2019.
Funding Information:
This research was supported in part by NSFC 61872247 , Shenzhen Peacock Talent Grant 827-000175 and Guangdong Natural Science Funds (Grant No. 2019A1515011064 ).
Publisher Copyright:
© 2021 Elsevier B.V.
PY - 2021/12
Y1 - 2021/12
N2 - 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%.
AB - 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%.
UR - http://www.scopus.com/inward/record.url?scp=85117120104&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85117120104&partnerID=8YFLogxK
U2 - 10.1016/j.dss.2021.113650
DO - 10.1016/j.dss.2021.113650
M3 - Article
AN - SCOPUS:85117120104
SN - 0167-9236
VL - 151
JO - Decision Support Systems
JF - Decision Support Systems
M1 - 113650
ER -