Bibliometric Analysis of Artificial Intelligence (AI) Applied to Energy, Agricultural, and Metal Commodities: A Critical Review, Trends, and Research Agenda

In recent years, financial markets have undergone significant transformations specifically, with the advent of diverse contracts, products and digital platforms in trading commodities further becoming increasingly prominent. Artificial Intelligence (AI), encompassing Machine Learning (ML) and Deep Learning (DL), has emerged as a powerful tool in analysing these markets. This study provides a comprehensive bibliometric analysis of 100 publications (2019–2023) from Q1-ranked journals extracted from the Scopus database, focusing on AI applications in commodities such as energy resources, agricultural products, and metals. Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol and advanced bibliometric tools such as VOSviewer and Bibliometrix-R, this research identifies key trends, contributions, and gaps in the field. The findings reveal growing international collaboration, a notable methodological diversity, and a dominance of techniques like Long Short-Term Memory (LSTM) networks for forecasting and Random Forest (RF) models for feature selection. Commodity types, including crude oil, gold, and agricultural products like corn and soybeans, are extensively studied. This study contributes to the literature by mapping the structure of AI research applied to commodities and identifying opportunities for advancing predictive accuracy, risk management, and portfolio optimization. For practitioners, it offers insights into leveraging cutting-edge AI techniques to address market dynamics. Future research should focus on integrating unstructured data, enhancing model interpretability, and exploring underrepresented commodities.