Hybrid Prediction Model for International Crude Oil Prices Based on EEMD and SE Reconstruction Methods

Abstract

Accurate prediction of crude oil prices can provide references for the energy economy and valuable guidance for investors and decision-makers in formulating strategies. However, due to the complexity and volatility of the crude oil market, achieving accurate and reliable
crude oil price forecasts is challenging. Therefore, this paper proposes a hybrid forecasting model for crude oil prices that combines Ensemble
Empirical Mode Decomposition (EEMD) and Sample Entropy (SE) reconstruction. Firstly, the daily closing price data of WTI crude oil futures from January 2, 2018, to March 21, 2024, is selected. The EEMD method is used to decompose the original data, and the decomposed
sub-sequences are reconstructed and merged into high-frequency, mid-frequency, and low-frequency sequences using Sample Entropy (SE).
Finally, these sequences are input into six machine learning models for prediction and comparison. The research results show that, firstly, by
comparing the R2, RMSE, MAE, and MAPE values, it can be seen that the forecasting ability of the EEMD-SE hybrid forecasting model
is significantly better than the EEMD hybrid forecasting model, indicating that the combination of SE methods can effectively improve the
models forecasting ability. Secondly, the EEMD-SE-LSTM model has higher prediction accuracy than other models. Finally, the comparison
of models reveals that the BP neural network exhibits the greatest improvement after SE reconstruction. Therefore, it is recommended to improve the crude oil futures price forecasting and risk warning system.