Forecasting crude oil markets

Li, Jiaqi; Alroomi, Azzam; Nikolopoulos, Konstantinos

Abstract

In this research daily crude oil data from U.S, Energy Information Administration from 2000-2019 is explored to test the forecasting accuracy by drawing the comparison between multiple models.
Forecasting models discussed in the research cover regression, artificial neural network (ANN), exponential smoothing (ES), and autoregressive integrated moving average (ARIMA). We primarily
aim to determine which mode provides the optimal forecasting results for WTI and Brent market, two major international light oil markets. The data is split into training, validation, and testing parts, with different purposes of modelling. Based on the adopted evaluation metrics, ARIMA model exhibits the optimal performance in validation data for both markets; while seasonal exponential smoothing model achieves the best 10-day and 20-day ahead forecasting.

Citation

Li, J., Alroomi, A., & Nikolopoulos, K. (2024). Forecasting crude oil markets. Journal of Econometrics and Statistics, 4(1), 15-51. https://doi.org/10.47509/JES.2024.v04i01.02

• Journal Article Type: Article
• Acceptance Date: Feb 22, 2024
• Online Publication Date: Apr 15, 2024
• Publication Date: Apr 15, 2024
• Deposit Date: Oct 16, 2024
• Publicly Available Date: Oct 18, 2024
• Journal: Journal of Econometrics and Statistics
• Print ISSN: 2583-0473
• Peer Reviewed: Peer Reviewed
• Volume: 4
• Issue: 1
• Pages: 15-51
• DOI: https://doi.org/10.47509/JES.2024.v04i01.02
• Public URL: https://durham-repository.worktribe.com/output/2960456
• Publisher URL: https://www.arfjournals.com/jes/issue/296