期刊名称：Journal of King Saud University @?C Computer and Information Sciences
印刷版ISSN：1319-1578
出版年度：2020
页码：1-7
DOI：10.1016/j.jksuci.2020.01.006
出版社：Elsevier
摘要：High frequency Bitcoin price series are often non-linear and non-stationary and hence forecasting the price of Bitcoin directly or by transformation using statistical models is subject to large errors. This paper presents an ensemble model using variational mode decomposition (VMD) and Generalized additive model (GAM) to forecast intraday Bitcoin price. To evaluate the performance of the constructed model, it is compared with an ensemble of empirical mode decomposition (EMD) and GAM. The results showed that VMD-GAM model performed better than the EMD-GAM ensemble model in terms of three evaluation metrics (root mean square error, mean absolute percentage error, and bias) used.
