A novel crude oil price trend prediction method: Machine learning classification algorithm based on multi-modal data features. (1st April 2022)

• Record Type: Journal Article
• Authors: He, Huizi; Sun, Mei; Li, Xiuming; Mensah, Isaac Adjei
• Is Part Of: Energy. Volume 244(2022)Part A
• Publication Date: 2022-04-01
• Subjects: Crude oil price prediction -- Multi-modal data features -- Machine learning -- Classification algorithm -- Variational mode decomposition; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2021.122706
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Reliable forecasting of crude oil price has received a prodigious attention by both investment companies and governments. Motivated by this issue, this paper seeks to propose a new hybrid forecasting model for crude oil price trend prediction. For this purpose, the crude oil price series is initially decomposed by variational mode decomposition algorithm, and the multi-modal data features are extracted based on the decomposed modes. The volatility of crude oil prices is simultaneously converted into trend symbols through symbolic time series analysis. Machine learning multi-classifier are then trained with multi-modal data features and historical volatility as input and trend symbols as output. The well-trained models are used to predict the trend symbols of West Texas Intermediate crude oil future price. Empirical results demonstrate that the proposed hybrid forecasting model outperforms its counterparts. Among the classifiers used, the hybrid prediction model using support vector machine classifier exhibits superior predictive ability. The accuracy of the proposed model for predicting high volatility of crude oil prices is evidenced to be better than that of low volatility. Highlights: A novel hybrid prediction model is proposed based on VMD and ML algorithms. Five multi-modal data feature indices are established based on IMFs of prices. The forecasting accuracy is elevated by introducing multi-modal data features. Trend symbols of prices are predicted by ML multi-classifiers. Classification performs better than regression in forecasting price trend.