Based on GCT-RFE Modeling Research on Driving Mechanisms of Crude Oil Prices

Guangjie Liu; Junjie Zhao; Jinping Zhang

doi:10.54097/mcf8jf71

Authors

Guangjie Liu
Junjie Zhao
Jinping Zhang

DOI:

https://doi.org/10.54097/mcf8jf71

Keywords:

Crude Oil Prices, Drivers, Granger Causality Test, Two-stage Model.

Abstract

This paper discusses the shortcomings of traditional econometric methods in analyzing the nonlinear characteristics of the oil market, and proposes a new strategy based on AI and machine learning. We construct an analytical framework covering eight dimensions of finance, macroeconomics, inventory, policy uncertainty, technical indicators, supply and demand, and geopolitics, involving a total of 52 predictors. Through ADF test and differential processing, we ensure the stability of the data. Using the two-stage model, we screened out the key factors in 52 indicators through GCT, and further screened out 9 main indicators by RFE algorithm. Through KFold cross validation, we verify the robustness of this model and prove that it has a high degree of accuracy in predicting future oil prices and market fluctuations.

Downloads

Download data is not yet available.

References

[1] Ha J, Kose M A, Ohnsorge F, et al. Understanding the global drivers of inflation: How important are oil prices? [J]. Energy Economics, 2023, 127: 107096.

[2] Huang B, Sun Y, Wang S. A new two-stage approach with boosting and model averaging for interval-valued crude oil prices forecasting in uncertainty environments [J]. Frontiers in Energy Research, 2021, 9: 707937.

[3] Obadi S M, Korcek M. The crude oil price and speculations: Investigation using granger causality test [J]. International Journal of Energy Economics and Policy, 2018, 8 (3): 275-282.

[4] He Y, Han A, Hong Y, et al. Forecasting crude oil price intervals and return volatility via autoregressive conditional interval models [J]. Econometric Reviews, 2021, 40 (6): 584-606.

[5] Cheng X, Wu P, Liao S S, et al. An integrated model for crude oil forecasting: Causality assessment and technical efficiency [J]. Energy Economics, 2023, 117: 106467.

[6] Indupurnahayu I, Setiawan E B, Agusinta L, et al. Changes in demand and supply of the crude oil market during the COVID-19 pandemic and its effects on the natural gas market [J]. International Journal of Energy Economics and Policy, 2021, 11 (3): 1-6.

[7] Chen Y C, Huang W C. Constructing a stock-price forecast CNN model with gold and crude oil indicators [J]. Applied Soft Computing, 2021, 112: 107760.

[8] Sun C, Min J, Sun J, et al. The role of China's crude oil futures in world oil futures market and China's financial market [J]. Energy Economics, 2023, 120: 106619.

[9] Balcilar M, Bekiros S, Gupta R. The role of news-based uncertainty indices in predicting oil markets: a hybrid nonparametric quantile causality method [J]. Empirical Economics, 2017, 53: 879-889.

[10] Su C W, Huang S W, Qin M, et al. Does crude oil price stimulate economic policy uncertainty in BRICS? [J]. Pacific-Basin Finance Journal, 2021, 66: 101519.

[11] Li S, Tu D, Zeng Y, et al. Does geopolitical risk matter in crude oil and stock markets? Evidence from disaggregated data [J]. Energy Economics, 2022, 113: 106191.

[12] Masaadeh A H, Dundar B, Samuelson M I, et al. Bilateral Somatically Derived Germ Cell Tumors With 12p Gains Arising in High-grade Serous Carcinomas of the Ovary: A Case Report and Review of the Literature [J]. International Journal of Gynecological Pathology, 2024: 10.1097.