期刊
IEEE ACCESS
卷 11, 期 -, 页码 14841-14858出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2023.3239924
关键词
Predictive models; Deep learning; Time-frequency analysis; Neural networks; Ensemble learning; Data mining; Adaptation models; Commodity futures price; ensemble learning; ensemble empirical mode decomposition; combination forecasting; deep learning; machine learning
This paper proposes an EEMD-Hurst-LSTM prediction method based on the ensemble learning framework for the prediction of typical commodities in China's commodity futures market. The method utilizes EEMD and the adaptive fractal Hurst index to incorporate new features into the LSTM model, improving its correlation detection with the external market. The results show that the EEMD-Hurst-LSTM method outperforms other models in predictive performance and provides a superior trading strategy with better returns and risk control.
This paper proposes an EEMD-Hurst-LSTM prediction method based on the ensemble learning framework, which is applied to the prediction of typical commodities in China's commodity futures market. This method performs ensemble empirical mode decomposition (EEMD) on commodity futures prices, and incorporates the components obtained by EEMD decomposition and the adaptive fractal Hurst index calculated by using intraday high-frequency data as new features into the LSTM model to decompose its correlation with the external market to detect changes in market conditions. The results show that the EEMD-Hurst-LSTM method has better predictive performance compared to other horizontal single models and longitudinal deep learning combined models. Meanwhile, the trading strategy designed according to this ensemble model can obtain more returns than other trading strategies and have the best risk control level. The research of this paper provides important implications for the trend following of commodity markets and the investment risk management of statistical arbitrage strategies.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据