The role of AI in (Re)Shaping energy Finance: A systematic literature review

Energy finance is an interdisciplinary, rapidly evolving field integrating finance, economics, and energy systems to address complex challenges in market dynamics, sustainability, and policy-making amidst global energy transitions to net zero. Recent advances in artificial intelligence have reshaped energy finance research and practice, but no prior study has systematically examined how these methods have been applied across the field or what value they have brought. This paper provides a comprehensive review of approximately 700 academic studies published over the past five years, analyzing the diffusion and contribution of AI techniques across the six established thematic areas proposed by Zhang et al. (2018). While machine learning models are increasingly adopted, especially in forecasting applications, and often outperform classical econometric approaches in terms of accuracy, their use remains uneven. In some cases, methodological choices are clearly adapted to the structure of the data and the objective of the study, while in others, the implementation of complex ML algorithms lacks contextual justification or interpretability. More importantly, the review highlights a major gap, namely recent approaches such as explainable AI and causal machine learning are almost entirely absent, despite their potential to enhance transparency, support causal inference, and inform energy-related financial decisions. By identifying where AI has already contributed, where it remains underused, and how it could be better integrated, the paper offers a structured and forward-looking perspective on the evolving relationship between artificial intelligence and energy finance.