🤖 AI Summary
This study presents a systematic review of recent advances and challenges in applying diffusion generative models to financial data modeling, addressing the notable absence of dedicated surveys in this domain. Focusing on canonical financial data types—including time series, limit order books, and tabular data—the work synthesizes existing approaches in terms of modeling objectives, technical methodologies, and practical applications. It integrates theoretical frameworks from diffusion processes, stochastic differential equations, Itô calculus, and stochastic control to provide a cohesive foundation. As the first survey specifically devoted to diffusion models in finance, this paper establishes a structured taxonomy and releases an open-source repository of relevant resources, thereby offering both theoretical guidance and practical support for future research in this emerging field.
📝 Abstract
Diffusion generative models have rapidly emerged as powerful tools for modeling complex financial data. Their appeal is both structural and practical: they offer stable likelihood-based training, strong mode coverage, flexible conditioning, and a stochastic-differential-equation formulation that aligns naturally with the Itô calculus and stochastic control frameworks widely used in finance. This survey reviews the growing literature on diffusion-family generative models for financial applications. We organize prior work primarily by financial data type, covering time series, limit order books, tabular data, and other structured financial objects, while discussing the modeling goals and application contexts that arise within each category. To the best of our knowledge, this is the first survey dedicated specifically to diffusion-family models for financial data. For more detailed information, we have open-sourced a repository https://github.com/ZhuoHan1998/Diffusion-Models-In-Finance.