Point and interval forecasting system for crude oil price based on complete ensemble extreme-point symmetric mode decomposition with adaptive noise and intelligent optimization algorithm

Abstract

Stable and accurate prediction of crude oil prices is critical to national security, economic development, and even international relations, against the background of the COVID-19 and Russia–Ukraine war. Therefore, a memory-based hybrid forecasting system is established for point prediction and interval prediction of crude oil prices in this research, which more thoroughly separates the noise in the raw data and achieves superior prediction performance. There are five main steps in the proposed model: decomposing the raw data into intrinsic mode functions (IMFs) through our new data preprocessing technique complete ensemble extreme-point symmetric mode decomposition with adaptive noise (CEESMDAN), ensemble of IMFs based on memory features, prediction of reconstructed components, error correction via grey wolf optimizer (GWO) for final point prediction, obtaining interval prediction by multi-objective grey wolf optimizer (MOGWO). The empirical results prove that the proposed model has excellent accuracy, robustness, and generalization in both point prediction and interval prediction, compared with various baseline models.