Do EEMD based decomposition-ensemble models indeed improve prediction for crude oil futures prices?

Abstract

The ensemble empirical mode decomposition (EEMD) based decomposition-ensemble models are widely applied to crude oil futures prices prediction. However, we argue whether EEMD really improves the prediction as the one-time decomposition would cause the exposure of future features, which may result in a misleadingly high accuracy. Therefore, a sliding decomposition-ensemble paradigm SW-EEMD-RVFL is proposed, which conducts the decomposition only of historical series in the sliding window for each forecasting iteration. The random vector functional link (RVFL) neural network is employed as the forecasting approach. The Brent and West Texas Intermediate (WTI) crude oil futures are taken to verify the model by comprehensively comparing individual econometric, artificial intelligence models and their hybrid forms. The findings show that, although hybrid models perform well in the in-sample data, SW-EEMD based models cannot outperform neither the EEMD based models or individual models in the out-of-sample data. EEMD cannot improve the prediction when only based on the decomposition of historical series, which is not consistent with most researches. Except only focusing on the improving accuracy, this work also gives possible explanations of the forecasting results from both methodologies and theories, as well as demonstrates the Efficient Markets Hypothesis (EMH) in terms of artificial intelligence methods.