Journal
KNOWLEDGE-BASED SYSTEMS
Volume 213, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.knosys.2020.106669
Keywords
Crude oil price forecasting; Variational mode decomposition; Long short-term memory network
Categories
Funding
- National Natural Science Foundation of China [61973332]
Ask authors/readers for more resources
An improved VMD-parameter selection rule and signal-energy based moving-window strategy were proposed, and a VMD-LSTM-MW model was established, demonstrating its effectiveness, validity, and superiority through experiments.
Crude oil price prediction helps to get a better understanding of the global economic situation. Recently, variational mode decomposition (VMD) is introduced into the field of crude oil price forecasting. However, there is a lack of general selection rule for VMD-parameter and the widely adopted one-time decomposition strategy seems not suitable for practical application. Thus, an improved signal-energy based (ISE) rule is proposed as an improvement of the existing signal-energy based (SE) rule for the VMD-parameter selection. The moving-window strategy is put forward as a supplement for the decomposition strategy. Finally, a prediction model (VMD-LSTM-MW model) is built by combining the VMD, the long short-term memory (LSTM) network, and the moving-window strategy. The effectiveness of the ISE rule, the validity of the moving-window strategy, and the superiority of the VMD-LSTM-MW model are demonstrated by conducting monthly and daily crude oil price prediction experiments. (C) 2020 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available