文献类型：期刊文献

英文题名：Study on influencing factors and forecast of global crude oil prices based on the hybrid model

作者：Wang, Donghua[1];Fang, Tianhui[2]

机构：[1]East China Univ Sci & Technol, Sch Business, Shanghai 200237, Peoples R China;[2]Shanghai Univ Finance & Econ, Shanghai Inst Int Finance & Econ, Sch Finance, Shanghai 200433, Peoples R China

年份：2025

卷号：328

外文期刊名：ENERGY

收录：;EI(收录号：20252118457048);WOS:【SCI-EXPANDED(收录号:WOS:001498938100018)】；

基金：This research was supported by National Natural Science Foundation of China (Grant No.72171086) and Innovation Program of Shanghai Municipal Education Commission (Grant No. 2023SKZD09) .

语种：英文

外文关键词：Midstream and downstream products of crude; oil; LASSO model; TVP model; LASSO-TVP model

摘要：As one of the most important strategic resources in the world today, the influencing factors of crude oil have always been the focus of international attention. In this paper, not only the traditional factors were considered, but also the midstream and downstream products of crude oil factor was introduced, referring to the industry's viewpoint, when analyzing the influencing factors of global crude oil prices. Moreover, Least Absolute Shrinkage and Selection Operator (LASSO) model was used to filter and analyze these factors and Least Absolute Shrinkage and Selection Operator-Time Varying Parameter (LASSO-TVP) model was used to forecast global crude oil prices finally. The results showed that global crude oil prices were influenced by different influencing factors, and the same influencing factor had different effects on global crude oil prices in different time periods. Among them, midstream and downstream products of crude oil had a strong influence on global crude oil prices. It was further found that the LASSO-TVP model had the best predictive effect, indicating that the LASSO-TVP model could significantly improve the forecasting effectiveness of LASSO model and TVP model, and accurately forecast global crude oil prices.