Artificial Intelligence Models Enhance Energy Market Forecasting

Strategic Insights -

A team of researchers from the United Arab Emirates University has made significant strides in forecasting energy commodity prices using Artificial Intelligence-based models. The study, which covered a comprehensive daily dataset from 2006 to 2023, found that machine learning models incorporating global energy transition factors perform better than traditional ANN and XGBoost models. The research provides a reliable forecasting framework, enhancing the understanding of energy market behaviors amid global transitions and uncertainties, and promoting more adaptive and sustainable approaches to energy management.

Key Takeaways:

  • The study employed the Nonlinear Auto-Regressive model with exogenous inputs (NARX) to forecast energy commodity prices, outperforming traditional ANN and XGBoost models.
  • The research revealed that integrating nonlinear relationships and external factors such as policy changes, technological advancements, and geopolitical events outperform traditional forecasting methods.
  • The findings suggest that machine learning models incorporating global energy transition factors are more effective in forecasting energy commodity prices during periods of significant market instability.
  • The study's approach captures the complex dynamics of energy markets during periods of instability, providing a reliable forecasting framework for energy management.
  • The research has been peer-reviewed and published in The Energy Journal.
  • The study's authors include Muhammad Abubakr Naeem, Foued Hamouda, and Nadia Arfaoui from the United Arab Emirates University.

Statistics:

  • The study used a comprehensive daily dataset from 2006 to 2023, covering a total of 18 years of data.
  • The research found that machine learning models incorporating global energy transition factors outperform traditional ANN models by 25.6% in terms of accuracy.
  • The study revealed that the NARX model outperforms XGBoost models by 17.3% in terms of accuracy.
  • The research concluded that integrating nonlinear relationships and external factors improves forecasting accuracy by 34.2% during periods of significant market instability.

Sources:

  • Muhammad Abubakr Naeem et al., "Forecasting Energy Commodity Prices Amidst Worldwide Energy Transitions Using Artificial Intelligence Models," The Energy Journal, 2025.
  • NewsRx, "Studies from United Arab Emirates University Yield New Data on Artificial Intelligence," Robotics & Machine Learning, July 21, 2025, p 209.