Methodological review demonstrates advancements in machine learning models across financial markets, highlighting key challenges in model interpretability, robustness, and economic integration.
Machine learning (ML) and the proliferation of large, granular, and unstructured data are reshaping how financial questions are posed and answered. Methods that relax the linearity, low dimensionality, and rigid distributional assumptions of classical econometrics are now applied across asset pricing, derivative valuation, forecasting, trading, risk management, and corporate finance. This special issue assembles nine contributions, which we organise around three themes: methodological advances in deep learning; ML for forecasting and dynamic decision-making; and explainable and applied ML in corporate finance and markets. Across the issue, common concerns emerge: interpretability, robustness across regimes, data quality, and the integration of economic structure with flexible learning. We introduce each contribution, situate it within the broader literature, and close by outlining open challenges and directions for future research.
No takes yet. Share an insight, caveat, or question.
Kyriakou et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: