Forecasting crude oil prices using reservoir computing models

• Verfasst von: Kumar, Kaushal [VerfasserIn]
• Titel: Forecasting crude oil prices using reservoir computing models
• Verf.angabe: Kaushal Kumar
• E-Jahr: 2024
• Jahr: 28 November 2024
• Umfang: 21 S.
• Illustrationen: Illustrationen
• Fussnoten: Gesehen am 17.07.2025
• Titel Quelle: Enthalten in: Computational economics
• Ort Quelle: Dordrecht [u.a.] : Springer Science + Business Media B.V., 1988
• Jahr Quelle: 2024
• Band/Heft Quelle: (2024), early view, Seite [1-21]
• ISSN Quelle: 1572-9974
• DOI: doi:10.1007/s10614-024-10797-w
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Computational Economics
• Sach-SW: Computational Intelligence
• Sach-SW: Computational Neuroscience
• Sach-SW: Computer Science
• Sach-SW: Crude oil prices
• Sach-SW: Energy Informatics
• Sach-SW: Financial market prediction
• Sach-SW: Forecasting
• Sach-SW: Information Processing
• Sach-SW: Reservoir computing
• Sach-SW: Time series analysis
• K10plus-PPN: 1931000867

Abstract

Accurate forecasting of crude oil prices is crucial for informed financial decision-making. This study presents a cutting-edge Reservoir Computing (RC) model specifically designed for precise crude oil price predictions, outperforming traditional methods such as ARIMA, LSTM, and GRU. Using daily closing prices from major indices spanning January 2010 to December 2023, we conducted a thorough evaluation. The RC model consistently demonstrates superior accuracy and computational efficiency. Quantitative metrics reveal the RC model’s dominance with a Mean Absolute Error (MAE) of 0.0094, Mean Squared Error (MSE) of 0.00035, Root Mean Squared Error (RMSE) of 0.0196, and a notably low Mean Absolute Percentage Error (MAPE) of $$1.450\%$$. Additionally, the RC model’s runtime of 1.11 s underscores its computational efficiency, far surpassing ARIMA (493.22 s), LSTM (423.55 s), and GRU (15.73 s). During periods of economic disruption, such as the COVID-19 lockdowns, the RC model effectively captured sharp price fluctuations, highlighting its robust forecasting capability. These findings emphasize the RC model’s potential as a reliable tool for enhancing decision-making processes in the dynamic energy market, particularly for real-time applications such as infectious disease case count forecasting. This study advocates for the broader adoption of Reservoir Computing models to improve predictive accuracy and operational efficiency in energy economics.