Forecasting crude oil futures prices using BiLSTM-Attention-CNN model with Wavelet transform

• Published in: Applied soft computing Vol. 130; p. 109723
• Main Authors: Lin, Yu, Chen, Kechi, Zhang, Xi, Tan, Bin, Lu, Qin
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2022
• Subjects: Attention mechanism; Bidirectional long short-term memory network; Convolutional neural network; Crude oil futures price forecasting; Wavelet transform; Attention mechanism; Wavelet transform; Bidirectional long short-term memory network; Convolutional neural network; Crude oil futures price forecasting

In this study, a novel hybrid model for forecasting crude oil futures price time series is proposed. The combination of Bidirectional long short-term memory network (BiLSTM), Attention mechanism and Convolution neural network (CNN) is used. Based on the principle of deep learning (DL) and wavelet tr...