Machine Learning for Trading
Code for Machine Learning for Trading, 3rd edition — from data sourcing to live execution. observed · 2026-10-19
Health v2 · maintenance only
94/100
- Activity 100
- Release rhythm 84
- Longevity 100
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: 58
- age_days: 3086
- days_rel: 30
- days_push: 2
- n_releases_24m: 2
Adoption not part of the score
21452 stars · 5718 forks observed · 2026-10-19
What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-19, confidence 0.97
Machine Learning for Trading is an open‑source Python ecosystem that provides end‑to‑end tools for quantitative finance, from market data acquisition to feature engineering, model training, backtesting, and live trading. It powers the examples in Stefan Jansen’s ML‑for‑Trading book and is organized into several composable libraries.
Use cases
- fetch and store historical market data from multiple providers
- engineer leakage‑free features and labels for financial time‑series
- train and evaluate deep learning models for price prediction
- run event‑driven backtests with realistic execution semantics
- deploy a strategy to a live broker such as Interactive Brokers or Alpaca
When to choose
- you need a production‑grade, end‑to‑end workflow for quantitative research and live trading
- you work in Python and want tightly integrated libraries for data, features, models, backtesting and deployment
- you prefer open‑source tools with extensive documentation and community support
When to avoid
- your stack is not Python‑centric or requires low‑level C++/Java implementations
- you need ultra‑low‑latency execution beyond what the library’s event‑driven engine provides
- you are looking for a single‑purpose library rather than a full workflow suite
Facets
library · maturity active
machine-learning simulation http-client data-science artificial-intelligence machine-learning python windows cross-platform quantitative-trading finance-data feature-engineering backtesting live-deployment synthetic-data ml4t data-ingestion finance trading linux macos
10 sources
- readme: https://github.com/stefan-jansen/machine-learning-for-trading · fetched 2026-10-19 · d49442cb3b47
- homepage: https://ml4trading.io · fetched 2026-10-05 · a300877f7642
- site_page: https://ml4trading.io/about · fetched 2026-10-05 · a1defe059da6
- site_page: https://ml4trading.io/docs/data · fetched 2026-10-05 · ba8a9ec5cfd2
- site_page: https://ml4trading.io/docs/engineer · fetched 2026-10-05 · 9fa0747f91a0
- site_page: https://ml4trading.io/docs/models · fetched 2026-10-05 · d93352c3e5da
- site_page: https://ml4trading.io/docs/diagnostic · fetched 2026-10-05 · e12b329c7c49
- site_page: https://ml4trading.io/docs/backtest · fetched 2026-10-05 · 9922020d0860
- site_page: https://ml4trading.io/libraries · fetched 2026-10-05 · bdbd536358dc
- site_page: https://ml4trading.io/chapters · fetched 2026-10-05 · 36f6ca9c8566
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| stefan-jansen/machine-learning-for-trading | main | 94 |
| stefan-jansen/synthetic-data-for-finance | examples | 32 |
For agents
markdown · JSON · MCP: product_card(name="stefan-jansen/machine-learning-for-trading")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem