Forecasting gold price using a novel hybrid model with ICEEMDAN and LSTM-CNN-CBAM

作者：

Highlights：

• Adopt a novel hybrid model with frequency decomposition for gold prices prediction.

• Use the improved CEEMDAN (ICEEMDAN) to improve the prediction performance.

• Pass the inspection of standard measurement and MCS test.

• Show remarkable superiority in forecasting accuracy over compared models.

摘要

•Adopt a novel hybrid model with frequency decomposition for gold prices prediction.•Use the improved CEEMDAN (ICEEMDAN) to improve the prediction performance.•Pass the inspection of standard measurement and MCS test.•Show remarkable superiority in forecasting accuracy over compared models.

论文关键词：Gold price prediction,Improved Complete Ensemble Empirical Mode Decomposition with adaptive noise (ICEEMDAN),Long Short-Term Memory (LSTM),Convolutional Neural Networks (CNN),Convolutional Block Attention Module (CBAM),Model Confidence Set (MCS) test

论文评审过程：Received 21 June 2021, Revised 3 March 2022, Accepted 9 June 2022, Available online 13 June 2022, Version of Record 24 June 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117847