Geopolitical risk and crude oil price predictability: Novel decomposition ensemble approach based ternary interval number series

Ye Li, Yiyan Chen and Hooi Hooi Lean

Resources Policy, 2024, vol. 92, issue C

Abstract: This study presents a forecast of the ternary interval number series of crude oil prices, including both mean and extreme. In contrast to the previous studies that usually rely on a single method for forecasting, this study combines multivariate empirical mode decomposition, back-propagation neural network, long short-term memory network, and least squares support vector regression, to put forward a decomposition ensemble model for the ternary interval. The method takes full advantage of different models to match the reconstructed subsequence, thus improving the accuracy and stability of the prediction. Moreover, to comprehensively understand the role of geopolitical risk in crude oil price forecasting, this study analyzes the heterogeneity of different types of geopolitical risk in various crude oil price forecasts. Based on the prediction results, our proposed method demonstrates favorable in-sample and out-of-sample prediction capabilities under different evaluation indexes. The prediction results of the total index show that the out-of-sample prediction accuracy for geopolitical risk in Brent crude oil is superior to that of West Texas Intermediate. In terms of the sub-indices (geopolitical action and threat), the out-of-sample prediction of geopolitical action surpasses that of geopolitical threat for both crude oils. On the other hand, the out-of-sample prediction of both geopolitical action and geopolitical threat is more accurate for Brent crude oil than West Texas Intermediate. The research conducted in this manuscript introduces a new perspective for forecasting crude oil prices based on geopolitical risk.

Keywords: Geopolitical risk; Crude oil price forecasting; Ternary interval numbers; Neural network model; Multivariate empirical mode decomposition (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0301420724003337
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:jrpoli:v:92:y:2024:i:c:s0301420724003337

DOI: 10.1016/j.resourpol.2024.104966

Access Statistics for this article

Resources Policy is currently edited by R. G. Eggert

More articles in Resources Policy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().