This study investigates the effectiveness of forecasting energy commodity prices using Artificial Intelligence-based models that account for the transition to cleaner energy sources during periods of significant market instability, such as the COVID-19 pandemic and the Russia-Ukraine conflict. Employing the Nonlinear Auto-Regressive model with exogenous inputs (NARX) over a comprehensive daily dataset from 2006 to 2023, the results reveal that machine learning models incorporating global energy transition factors perform better than traditional ANN and XGBoost models. The findings also reveal that integrating nonlinear relationships and external factors such as policy changes, technological advancements, and geopolitical events outperform traditional forecasting methods. This approach captures the complex dynamics of energy markets during periods of instability. By providing a reliable forecasting framework, this study enhances the understanding of energy market behaviors amid global transitions and uncertainties, promoting more adaptive and sustainable approaches to energy management.
AjmiH.ArfaouiN.SaciK.2021. “Volatility Transmission across International Markets Amid COVID 19 Pandemic.”Studies in Economics and Finance38 (5): 926–45. doi:10.1108/SEF- 11-2020-0449.
2.
AnW.WangL.ZhangD.2023. “Comprehensive Commodity Price Forecasting Framework Using Text Mining Methods.”Journal of Forecasting42 (7): 1865–88. doi:10.1002/for.2985.
3.
AnwerZ.KhanA.NaeemM. A.TiwariA. K.2025. “Modelling Systemic Risk of Energy and Non-Energy Commodity Markets during the COVID-19 Pandemic.”Annals of Operations Research345: 1193–227. doi:10.1007/s10479-022-04879-x.
4.
ArfaouiN.RoubaudD.NaeemM. A.2025. “Energy Transition Metals, Clean and Dirty Energy Markets: A Quantile-on-Quantile Risk Transmission Analysis of Market Dynamics.”Energy Economics 143: 108250.
5.
AuneF. R.GolombekR.2021. “Are Carbon Prices Redundant in the 2030 EU Climate and Energy Policy Package?”The Energy Journal42 (3): 225–64. doi:10.5547/01956574.42.3.faun.
6.
BelaïdF.2024. “Decarbonizing the Residential Sector: How Prominent is Household Energy-Saving Behavior in Decision Making?”The Energy Journal45 (1): 125–48. doi:10.5547/01956574.45.1.fbel.
7.
Ben AmeurH.BoubakerS.FtitiZ.LouhichiW.TissaouiK.2024. “Forecasting Commodity Prices: Empirical Evidence Using Deep Learning Tools.”Annals of Operations Research339: 349–67. doi:10.1007/s10479-022-05076-6.
8.
Ben JabeurS.Mefteh-WaliS.VivianiJ. L.2021. “Forecasting Gold Price with the XGBoost Algorithm and SHAP Interaction Values.”Annals of Operations Research334 (1–3): 679–99. doi:10.1007/s10479-021-04187-w.
9.
BigernaS.D’ErricoM. C.PolinoriP.SimshauserP.2023. “Net-Zero Policy vs Energy Security: The Impact on GCC Countries.”The Energy Journal44 (1_suppl): 1–32. doi:10.5547/01956574. 44.SI1.sbig.
10.
Carlos MuñozJ.Oliva H.S.SaumaE.2023. “Effect of Combining Carbon Policies and Price Controls in Cross-Border Trade of Energy on Renewable Generation Investments.”The Energy Journal45 (1): 81–103. doi:10.5547/01956574.45.1.jmun.
11.
CostaA. B. R.FerreiraP. C. G.GaglianoneW. P.GuillénO. T. C.IsslerJ. V.LinY.2021. “Machine Learning and Oil Price Point and Density Forecasting.”Energy Economics102: 105494. doi:10.1016/j.eneco.2021.105494.
12.
DieboldF. X.MarianoR. S.1995. “Comparing Predictive Accuracy.”Journal of Business and Economic Statistics13 (3): 253–63. doi:10.1080/07350015.1995.10524599.
13.
DuttaA.2017. “Oil Price Uncertainty and Clean Energy Stock Returns: New Evidence from Crude Oil Volatility Index.”Journal of Cleaner Production164: 1157–66. doi:10.1016/j.jclepro.2017.07.050.
FanX.WangL.LiS.2016. “Predicting Chaotic Coal Prices Using a Multi-Layer Perceptron Network Model.”Resources Policy50: 86–92. doi:10.1016/j.resourpol.2016.08.009.
16.
ForoutanP.LahmiriS.2024. “Deep Learning Systems for Forecasting the Prices of Crude Oil and Precious Metals.”Financial Innovation10 (1): 111. doi:10.1186/s40854-024-00637-z.
17.
FosterE.ContestabileM.BlazquezJ.ManzanoB.WorkmanM.ShahN.2017. “The Unstudied Barriers to Widespread Renewable Energy Deployment: Fossil Fuel Price Responses.”Energy Policy103: 258–64. doi:10.1016/j.enpol.2016.12.050.
18.
GevreyM.DimopoulosI.LekS.2003. “Review and Comparison of Methods to Study the Contribution of Variables in Artificial Neural Network Models.”Ecological Modelling160 (3): 249–64. doi:10.1016/S0304-3800(02)00257-0.
19.
GhoddusiH.CreamerG. G.RafizadehN.2019. “Machine Learning in Energy Economics and Finance: A Review.”Energy Economics81: 709–727. doi:10.1016/j.eneco.2019.05.006.
GöncüA.KuzubaşT. U.SaltoğluB.2024. “Predicting Oil Prices: A Comparative Analysis of Machine Learning and Image Recognition Algorithms for Trend Prediction.”Finance Research Letters67: 105874. doi:10.1016/j.frl.2024.105874.
22.
GongX.GuanK.ChenQ.2022. “The Role of Textual Analysis in Oil Futures Price Forecasting Based on Machine Learning Approach.”Journal of Futures Markets42 (10): 1987–2017. doi:10.1002/fut.22367.
23.
GoodarziS.PereraH. N.BunnD.2019. “The Impact of Renewable Energy Forecast Errors on Imbalance Volumes and Electricity Spot Prices.”Energy Policy134: 110827. doi:10.1016/ j.enpol.2019.06.035.
24.
GuerraK.WelfleA.Gutiérrez-AlvarezR.FreerM.MaL.HaroP.2024. “The Role of Energy Storage in Great Britain’s Future Power System: Focus on Hydrogen and Biomass.”Applied Energy357: 122447. doi:10.1016/j.apenergy.2023.122447.
25.
HannaR.GrossR.2021. “How Do Energy Systems Model and Scenario Studies Explicitly Represent Socio-Economic, Political and Technological Disruption and Discontinuity? Implications for Policy and Practitioners.”Energy Policy149: 111984. doi:10.1016/j.enpol.2020.111984.
26.
HerreraG. P.ConstantinoM.TabakB. M.PistoriH.SuJ. J.NaranpanawaA.2019. “Long-Term Forecast of Energy Commodities Price Using Machine Learning.”Energy179: 214–21. doi:10.1016/j.energy.2019.04.077.
27.
HirthL.UeckerdtF.EdenhoferO.2016. “Why Wind Is Not Coal: On the Economics of Electricity Generation.”The Energy Journal37 (3): 1–28. doi:10.5547/01956574.37.3.lhir.
28.
HuangL.2022. “Motivation and Overview of Normalization in DNNs.” In Normalization Techniques in Deep Learning. Synthesis Lectures on Computer Vision, edited by HuangL., 11–18. Cham: Springer. doi:10.1007/978-3-031-14595-7_2.
29.
IRENA. 2022. Renewable Power Generation Costs. Abu Dhabi: International Renewable Energy Agency.
30.
IvanovskiK.HailemariamA.2021. “Forecasting the Dynamic Relationship between Crude Oil and Stock Prices since the 19th Century.”Journal of Commodity Markets24: 100169. doi:10.1016/j.jcomm.2021.100169.
31.
IzoninI.TkachenkoR.ShakhovskaN.IlchyshynB.SinghK. K.2022. “A Two-Step Data Normalization Approach for Improving Classification Accuracy in the Medical Diagnosis Domain.”Mathematics10 (11): 1–18. doi:10.3390/math10111942.
32.
JawadiF.2023. “Analyzing Commodity Prices in the Context of COVID-19, High Inflation, and the Ukrainian War: An Interview with James Hamilton.”The Energy Journal44 (1): 1–8. doi:10.5547/01956574.44.1.fjaw.
33.
KarkowskaR.UrjaszS.2023. “How Does the Russian-Ukrainian War Change Connectedness and Hedging Opportunities? Comparison between Dirty and Clean Energy Markets versus Global Stock Indices.”Journal of International Financial Markets, Institutions and Money85: 101768. doi:10.1016/j.intfin.2023.101768.
34.
KuncV.KlémaJ.2024. Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks, 1–107. http://arxiv.org/abs/2402.09092.
35.
LiY.JiangS.LiX.WangS. (2021). The role of news sentiment in oil futures returns and volatility forecasting: Data-decomposition based deep learning approach. Energy Economics95: 105140. https://doi.org/10.1016/j.eneco.2021.105140
NaeemM. A.ArfaouiN.2023. “Exploring Downside Risk Dependence across Energy Markets: Electricity, Conventional Energy, Carbon, and Clean Energy during Episodes of Market Crises.”Energy Economics127: 107082. doi:10.1016/j.eneco.2023.107082.
38.
NaeemM. A.GulR.AysanA. F.KayaniU.2024. “Oil Shocks and the Transmission of Higher-Moment Information in US Industry: Evidence from an Asymmetric Puzzle.”Borsa Istanbul Review24 (6): 1190–204. doi:10.1016/j.bir.2024.07.005.
39.
NaeemM. A.HamoudaF.KarimS.2024. “Tail Risk Spillover Effects in Commodity Markets: A Comparative Study of Crisis Periods.”Journal of Commodity Markets33: 100370. doi:10.1016/j.jcomm.2023.100370.
40.
PetersonR. A.CavanaughJ. E.2020. “Ordered Quantile Normalization: A Semiparametric Transformation Built for the Cross-Validation Era.”Journal of Applied Statistics47 (13–15): 2312–27. doi:10.1080/02664763.2019.1630372.
41.
PhilippidisG.ShutesL.M’BarekR.RonzonT.TabeauA.van MeijlH.2020. “Snakes and Ladders: World Development Pathways’ Synergies and Trade-Offs through the Lens of the Sustainable Development Goals.”Journal of Cleaner Production267: 122147. doi:10.1016/j.jclepro.2020.122147.
42.
PlanteM.StricklerG.2021. “Closer to One Great Pool? Evidence from Structural Breaks in Oil Price Differentials.”The Energy Journal42 (2): 1–30. doi:10.5547/01956574.42.2.mpla.
43.
ShahzadS. J. H.BouriE.RehmanM. U.NaeemM. A.SaeedT.2022. “Oil Price Risk Exposure of BRIC Stock Markets and Hedging Effectiveness.”Annals of Operations Research313: 145–70. doi:10.1007/s10479-021-04078-0.
44.
ShahzadU.SenguptaT.RaoA.CuiL.2024. “Forecasting Carbon Emissions Future Prices Using the Machine Learning Methods.”Annals of Operations Research337: 11. doi:10.1007/s10479-023-05188-7.
45.
SuM.NieY.LiJ.YangL.KimW.2024. “Futures Markets and the Baltic Dry Index: A Prediction Study Based on Deep Learning.”Research in International Business and Finance71: 102447. doi:10.1016/j.ribaf.2024.102447.
46.
UmarM.FaridS.NaeemM. A.2022. “Time-Frequency Connectedness among Clean-Energy Stocks and Fossil Fuel Markets: Comparison between Financial, Oil and Pandemic Crisis.”Energy240: 122702.
47.
WagnerA.RamentolE.SchirraF.MichaeliH.2022. “Short- and Long-Term Forecasting of Electricity Prices Using Embedding of Calendar Information in Neural Networks.”Journal of Commodity Markets28: 100246. doi:10.1016/j.jcomm.2022.100246.
48.
WangH.ZhangS.BiX.CliftR.2020. “Greenhouse Gas Emission Reduction Potential and Cost of Bioenergy in British Columbia, Canada.”Energy Policy138: 111285. doi:10.1016/j.enpol.2020.111285.
49.
WangN.GuoZ.ShangD.LiK.2024. “Carbon Trading Price Forecasting in Digitalization Social Change Era Using an Explainable Machine Learning Approach: The Case of China as Emerging Country Evidence.”Technological Forecasting and Social Change200: 123178. doi:10.1016/j.techfore.2023.123178.
50.
WuS.XiaG.LiuL.2023. “A Novel Decomposition Integration Model for Power Coal Price Forecasting.”Resources Policy80: 103259. doi:10.1016/j.resourpol.2022.103259.
51.
XiongT.BaoY.HuZ.2013. “Beyond One-Step-Ahead Forecasting: Evaluation of Alternative Multi-Step-Ahead Forecasting Models for Crude Oil Prices.”Energy Economics40: 405–415. doi:10.1016/j.eneco.2013.07.028.
52.
XuG.SchwarzP.YangH.2019. “Determining China’s CO2 Emissions Peak with a Dynamic Nonlinear Artificial Neural Network Approach and Scenario Analysis.”Energy Policy128: 752–62. doi:10.1016/j.enpol.2019.01.058.
53.
XuZ.MohsinM.UllahK.MaX.2023. “Using Econometric and Machine Learning Models to Forecast Crude Oil Prices: Insights from Economic History.”Resources Policy83: 103614. doi:10.1016/j.resourpol.2023.103614.
54.
YuJ.SpiliopoulosK.2023. “Normalization Effects on Deep Neural Networks.”Foundations of Data Science5 (3): 389–465. doi:10.3934/fods.2023004.
55.
ZargarF. N.MohnotR.HamoudaF.ArfaouiN.2024. “Risk Dynamics in Energy Transition: Evaluating Downside Risks and Interconnectedness in Fossil Fuel and Renewable Energy Markets.”Resources Policy92: 105032. doi:10.1016/j.resourpol.2024.105032.
56.
ZhangF.FleyehH.BalesC.2020. “A Hybrid Model Based on Bidirectional Long Short-Term Memory Neural Network and Catboost for Short-Term Electricity Spot Price Forecasting.”Journal of the Operational Research Society73 (2): 301–325. doi:10.1080/01605682.2020.1843976.
57.
ZhangK.CaoH.ThéJ.YuH.2022. “A Hybrid Model for Multi-Step Coal Price Forecasting Using Decomposition Technique and Deep Learning Algorithms.”Applied Energy306: 118011. doi:10.1016/j.apenergy.2021.118011.
58.
ZhengL.SunY.WangS.2024. “A Novel Interval-Based Hybrid Framework for Crude Oil Price Forecasting and Trading.”Energy Economics130: 107266. doi:10.1016/j.eneco.2023.107266.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
