Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Code for Machine Learning for Trading, 3rd edition — from data sourcing to live execution.
| Date | Stars |
|---|---|
| 2026-07-31 | 20189 |
| 2026-08-06 | 20314 |
| 2026-08-07 | 20324 |
| 2026-08-08 | 20343 |
| 2026-08-09 | 20358 |
| 2026-08-10 | 20375 |
| 2026-08-11 | 20398 |
| 2026-08-12 | 20416 |
| 2026-08-13 | 20433 |
| 2026-08-14 | 20440 |
| 2026-08-15 | 20452 |
| 2026-08-16 | 20471 |
| 2026-08-17 | 20487 |
| 2026-08-18 | 20496 |
| 2026-08-19 | 20514 |
| 2026-08-20 | 20545 |
| 2026-08-21 | 20565 |
| 2026-08-22 | 20577 |
| 2026-08-23 | 20586 |
| 2026-08-24 | 20599 |
| 2026-08-25 | 20632 |
| 2026-08-26 | 20647 |
| 2026-08-27 | 20681 |
| 2026-08-28 | 20708 |
| 2026-08-29 | 20711 |
| 2026-08-30 | 20732 |
| 2026-08-31 | 20742 |
| 2026-09-01 | 20747 |
| 2026-09-02 | 20754 |
| 2026-09-03 | 20770 |
| 2026-09-04 | 20777 |
| 2026-09-05 | 20782 |
| 2026-09-06 | 20798 |
| 2026-09-07 | 20814 |
| 2026-09-08 | 20839 |
| 2026-09-09 | 20848 |
| 2026-09-10 | 20858 |
| 2026-09-11 | 20863 |
| 2026-09-12 | 20870 |
| 2026-09-13 | 20885 |
| 2026-09-14 | 20894 |
| 2026-09-15 | 20903 |
| 2026-09-16 | 20913 |
| 2026-09-17 | 20920 |
| 2026-09-18 | 20927 |
| 2026-09-19 | 20935 |
| 2026-09-20 | 20946 |
| 2026-09-21 | 20962 |
| 2026-09-22 | 20971 |
| 2026-09-23 | 20983 |
| 2026-09-24 | 20998 |
| 2026-09-25 | 21016 |
| 2026-09-26 | 21037 |
| 2026-09-27 | 21072 |
| 2026-09-28 | 21092 |
| 2026-09-29 | 21117 |
| 2026-09-30 | 21133 |
| 2026-10-01 | 21181 |
| 2026-10-02 | 21202 |
| 2026-10-03 | 21203 |
| 2026-10-04 | 21214 |
| 2026-10-05 | 21226 |
| 2026-10-06 | 21242 |
| 2026-10-07 | 21252 |
| 2026-10-08 | 21259 |
| 2026-10-09 | 21267 |
| 2026-10-10 | 21288 |
| 2026-10-11 | 21294 |
| 2026-10-12 | 21306 |
| 2026-10-13 | 21333 |
| 2026-10-14 | 21343 |
| 2026-10-15 | 21360 |
| 2026-10-16 | 21371 |
| 2026-10-17 | 21388 |
| 2026-10-18 | 21433 |
| 2026-10-19 | 21459 |
| 2026-10-20 | 21475 |
| 2026-10-21 | 21486 |
| 2026-10-22 | 21511 |
| 2026-10-23 | 21523 |
| 2026-10-24 | 21533 |
| 2026-10-25 | 21542 |
| 2026-10-26 | 21553 |
| 2026-10-27 | 21580 |
| 2026-10-28 | 21616 |
| 2026-10-29 | 21627 |
| 2026-10-30 | 21640 |
| 2026-10-31 | 21647 |
| 2026-11-01 | 21662 |
| 2026-11-02 | 21675 |
| 2026-11-03 | 21689 |
| 2026-11-04 | 21708 |
Today
+19 stars today
This week
+92 stars this week
This month
+482 stars this month
Momentum
183.0
growth rate 0.43%/day
# Machine Learning for Trading, 3rd Edition **Build, test, and deploy ML-driven trading strategies, from data sourcing to live execution.** The code for [*Machine Learning for Trading, 3rd Edition*](https://amzn.to/4eigy2F) by [Stefan Jansen](https://www.linkedin.com/in/applied-ai/): 27 chapters and nine case studies, rebuilt from the ground up around one end-to-end workflow. How a research idea becomes a strategy you can run, and keep running, in a live market. <p align="center"> <a href="https://amzn.to/4eigy2F"><img src="assets/cover.png" width="45%" alt="Machine Learning for Trading, 3rd Edition"></a> </p> **Looking for the second edition?** It is complete and stable on the `second-edition` branch: `git checkout second-edition`, and everything is exactly where that book describes it. ## Contents - [What's new in the third edition](#whats-new-in-the-third-edition) - [Nine case studies](#nine-case-studies), the structural centerpiece of this edition - [Courses and workshops](#courses-and-workshops) - [The code, chapter by chapter](#the-code-chapter-by-chapter), 27 chapter guides - [Quick start](#quick-start): install, download the data, run your first notebook - [Companion resources](#companion-resources): primers, agent skills, and the six libraries - [Repository layout](#repository-layout) --- ## What's New in the Third Edition The whole book traces one path: from data infrastructure and strategy research, across an *evidence boundary* that separates tuning from evaluation, to deployment and monitoring, with a feedback loop that retrains, pauses, or retires a strategy as its edge decays. <p align="center"> <img src="assets/workflow.png" width="90%" alt="The ML4T workflow: data infrastructure and strategy research, an evidence boundary separating tuning from evaluation, and deployment with a retrain/pause/retire feedback loop"> </p> Where earlier editions moved technique by technique, the third edition runs that one process end to end, and adds substantial new material: - **A wider model toolkit**: from gradient boosting (XGBoost, LightGBM, CatBoost) to deep time-series architectures (PatchTST, iTransformer, TSMixer, TCN, Mamba) and newer tabular and latent-factor models (TabPFN, TabM, conditional and supervised autoencoders). - **Dedicated strategy-design chapters**: transaction costs and risk management are now full chapters, neither of which existed before, joining portfolio construction and strategy synthesis so a raw signal is carried through to a sized, cost- and risk-aware portfolio. - **A full production track**: live trading systems (Interactive Brokers, Alpaca, QuantConnect), MLOps and governance (drift detection, safe rollout, circuit breakers, feature stores, experiment tracking), and the operational reality of *running* strategies, not just building them. - **Generative AI**: retrieval-augmented generation grounded in SEC filings, knowledge graphs and Graph RAG, and autonomous, multi-agent research systems. - **Causal machine learning**: Double ML, Bayesian structural time series, and causal discovery for separating real effects from spurious correlation. - **Reinforcement learning**: optimal execution, market making with inventory, and deep hedging. - **Synthetic financial data**: TimeGAN, Tail-GAN, Sig-CWGAN, and diffusion-based generators for validation when history is short. Methodological rigor is treated as a first-class topic rather than an afterthought. The book draws an explicit line between exploration and confirmation, the *evidence boundary*, uses walk-forward cross-validation throughout, and confronts the multiple-testing and overfitting problems that quietly invalidate most backtests, with tools like the Deflated Sharpe Ratio, the Rademacher Anti-Serum, and White's Reality Check, plus conformal prediction for honest uncertainty estimates. The data layer moves to **Polars** for fast, expression-based manipulation, and every chapter ships in **reproducible Docker
Excerpt of 31,468 characters
Read on GitHub
Stefan Jansen · https://www.applied-ai.com · United States
360
4
Ryan Russell
3
Sebastian
2
Carlos Quiroga · Spain
2
franz101
1
1
h1pp0
1
Lee Hawthorn · Private · United Kingdom
1
Tomas Rampas · Czech Republic
1
mgh
1
Norbert Raus · dot.company · Poland
1
Prathab · Salesforce Inc. · India
1
Sherry
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e3973c0e88761cae, topic:finance, topic:quantitative-finance, topic:trading