Artificial intelligence in financial markets: a literature review and research agenda

Purpose This paper is targeted at researchers in the fields of economics and finance and presents a comprehensive literature review of artificial intelligence (AI) applications in finance, examining research published in leading finance and economics journals. Our analysis reveals significant advances in algorithmic trading, credit scoring, fraud detection and regulatory compliance while highlighting persistent challenges in model interpretability, fairness and systemic risk. Design/methodology/approach Our analysis encompasses 138 carefully selected papers published between January 2019 and December 2024, with an initial analysis of pre-prints and early 2025 publications to capture the latest trends. This study employs a structured literature review methodology, systematically searching top-tier finance and economics journals, including UTD24 Journals, FT50 Journals and additional leading publications in finance and economics. To maintain a clear economic perspective, we explicitly exclude purely technical computer science literature, focusing instead on papers that contribute to our understanding of AI's economic implications for financial markets. Findings Our synthesis reveals AI's dual impact that while models like advanced machine learning methods enhance predictive accuracy in asset pricing and expand credit access, they also introduce challenges in interpretability, algorithmic fairness and new vectors for systemic risk, such as algorithmic collusion. In China's unique regulatory environment, characterized by strict algorithmic disclosure requirements and quantitative trading thresholds, these challenges are particularly acute as regulators balance innovation with market stability concerns. Further research and policy development are needed to ensure AI's responsible integration into financial systems. Originality/value This paper provides a comprehensive review of AI in finance from an economic theory perspective, examining fundamental questions like algorithmic collusion, Nash equilibria among AI agents and cross-border data regulation. It offers a structured intellectual map and forward-looking research agenda with relevance for both developed and emerging markets.