EEMD-CNN-BiLSTM-QR Enabled Probability Density Forecasts for Crude Oil Price

The price of crude oil has been subject to periodical fluctuations as a consequence of changes in seasonal demand and supply, as well as weather, natural disasters, and global political unrest. Accurate forecast of crude oil prices is of utmost importance for decision-makers and industry players in the energy sector. Despite this, the volatility of crude oil prices contributes to the uncertainty of the energy industry, which was particularly challenging following the recent global spread of the COVID-19 pandemic as well as Russia-Ukraine conflicts. This paper aims to propose a hybrid modeling framework to deal with the volatility of crude oil prices, employing several well-established data analytics such as ensemble empirical mode decomposition (EEMD), convolutional neural network (CNN), and bidirectional long short-term memory (BiLSTM) integrated with quantile regression (QR), named as EEMD-CNN-BiLSTM-QR. Two sets of real-world data of crude oil prices from the West Texas Intermediate (WTI) and the Brent Crude Oil markets were employed to validate the EEMD-CNN-BiLSTM-QR hybrid modeling framework. An in-depth analysis was carried out with the prediction accuracy being calculated while the probability density forecast remains uncertain. The findings of this study demonstrated that the proposed EEMD-CNN-BiLSTM-QR modeling framework is superior to other tested models in terms of its ability to forecast crude oil prices. The novelty of this study stems mostly from the use of QR, which allows for the description of the conditional distribution of predicted variables and the extraction of more uncertain information for probability density forecast.