Denoising or distortion: Does decomposition-reconstruction modeling paradigm provide a reliable prediction for crude oil price time series?

Abstract

Reliable forecasting of the crude oil price has important implications for production planning, investment decisions and policy making. Though the effectiveness of denoising hybrid models in crude oil price forecasting has been widely demonstrated, we argue that the denoised series used for model fitting may be affected by the out-of-sample information due to the one-time denoising operation applied to the entire price series. To verify whether the denoising paradigm does improve the crude oil price forecasting, a rolling window mechanism is introduced into two denoising hybrid models based on ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD). The novel R-EEMD-RVFL and R-VMD-RVFL models with the random vector functional link (RVFL) neural network are proposed. Then, both monthly and weekly West Texas Intermediate crude oil spot prices are used for multi-step-forward prediction. The experiment reports that: Firstly, the prediction provided by conventional denoising hybrid models is unreliable due to the one-time denoising procedure. Secondly, the proposed R-VMD-RVFL model achieves superior and robust accuracies in both monthly and weekly crude oil price predictions, especially when the forecast horizon is relatively long. Furthermore, this study provides theoretical supports for the findings using the weak-form efficient market hypothesis and behavioral finance theory as well as technical analysis from the perspective of denoising methods.