Discover open-source algorithmic trading frameworks that combine AI signals with order execution
Find academic papers on reinforcement learning and LLM applications for financial markets
Locate datasets and exchange APIs to build and backtest a quantitative trading strategy
Explore tools for technical analysis that calculate indicators like moving averages and momentum signals
Awesome AI in Finance is a curated reading list of tools, research papers, datasets, and code projects that apply artificial intelligence and machine learning to financial markets. It is a community-maintained document, not runnable software, and its purpose is to help people discover what is available in this space. The list is organized into several categories. The Agents section covers AI trading systems where multiple AI models work together to analyze markets or make trades. The LLMs section focuses on large language model applications in finance, including projects that use language models to analyze earnings reports, generate trading signals, or simulate market behavior. There is also a section of academic research papers going back to 1900, tracing the history of mathematical approaches to market prediction, alongside more recent work on reinforcement learning for algorithmic trading. Other sections cover data sources (where to get financial data), exchange APIs (how to connect to trading platforms programmatically), tools for technical analysis such as libraries that calculate indicators like moving averages and momentum signals, and full trading system frameworks that combine these pieces. The list includes entries for both stock markets and cryptocurrency markets. A separate section links to courses and books on quantitative finance. The entries range from open-source GitHub repositories you can run yourself to published academic papers and external blog posts. Star ratings within the list indicate which entries the maintainer considers particularly notable. The project has a Discord community for discussion, and Chinese-language resources are available in a separate linked document. Contributions from the community to add new tools and papers are welcomed via pull requests. The full README is longer than what was shown.
← georgezouq on gitmyhub — every repo by this author, as a profile.
Verify against the repo before relying on details.