Generative AI and Machine Learning in Quantitative Finance

Recent advances in generative AI and machine learning have expanded the capabilities of quantitative finance, enabling improved forecasting, portfolio optimization, trading strategies, and risk analytics. Deep learning architectures and generative models are increasingly applied to complex financial datasets, offering new insights beyond traditional econometric approaches. However, the effective deployment of these methods requires careful empirical validation, robustness assessment, and understanding of associated risks. This Research Topic aims to provide a platform for research that advances both the development and practical evaluation of AI-driven financial models, while considering their stability, interpretability, and risk implications in real-world financial environments.The goal of this Research Topic is to encourage high-quality research on the application and quantitative evaluation of generative AI and machine learning in finance. We welcome studies that develop novel algorithms, assess model performance across different market conditions, analyze robustness under data shifts, and investigate risk implications of AI-based financial systems. Contributions may include empirical studies, methodological advancements, and quantitative frameworks for monitoring and managing model risk. By promoting research that integrates algorithmic innovation with practical evaluation and risk awareness, this collection aims to support the development of reliable and scalable AI solutions for financial markets and institutions.This Research Topic welcomes contributions on the development, application, and quantitative evaluation of generative AI and machine learning methods in quantitative finance. Relevant themes include, but are not limited to:- deep learning and generative modeling for financial time series;- portfolio optimization;- algorithmic trading;- asset pricing;- derivative valuation;- credit risk;- risk analytics.We particularly encourage studies that assess model performance under varying market conditions, examine robustness to regime shifts and data limitations, and explore quantitative approaches to model risk monitoring and governance. Submissions may include methodological innovations, empirical analyses using real-world financial data, comparative evaluations of algorithms, and frameworks for improving interpretability and stability of AI-driven financial systems. We are interested in Original Research articles, Review articles, Methods papers, and data-driven empirical studies that combine algorithmic innovation with sound statistical validation. Topic editors: Qinxu Ding, Xiaodan Dong Source: https://www.frontiersin.org/research-topics/78975/generative-ai-and-machine-learning-in-quantitative-finance