# AI4Finance-Foundation/FinRL-Trading

FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading

Repository: https://github.com/AI4Finance-Foundation/FinRL-Trading
Canonical: https://ross.abutalabs.com/products/finrl-trading
Homepage: https://ai4finance.org
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-reinforcement-learning, stock-trading, a2c-algorithm, ppo, ddpg, ensemble-strategy, stock-trading-strategy, automated-stock-trading, sharpe-ratio, finrl, portfolio, portfolio-allocation, stock-selection, finrl-x
Last push: 2026-05-02T15:12:44+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 80, release rhythm 44, longevity 100
- inputs: {"age_days": 2229, "days_push": 123, "days_rel": 161, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3592, forks 1062 (observed 2026-08-28T04:08:11.194025+00:00)

## What it is
FinRL-X is an open-source, AI-native modular infrastructure for quantitative trading that unifies data processing, strategy composition, backtesting, and broker execution through a weight-centric interface. It succeeds the original FinRL framework and supports ML-based stock selection, portfolio allocation, risk overlays, and live brokerage execution.

## Use cases
- backtest deep reinforcement learning trading strategies
- automate stock trading with machine learning
- build a portfolio allocation strategy with RL agents
- run live trading through a broker like Alpaca
- compare PPO, A2C, and DDPG trading agents
- select stocks and time trades with ML models
- evaluate strategies by Sharpe ratio

## When to choose
- you want a full-stack pipeline from data to live broker execution in Python
- you are researching deep reinforcement learning for trading
- you need modular, swappable strategy components with a consistent interface
- you want reproducible backtesting plus production deployment in one framework

## When to avoid
- you need a simple rule-based backtester without ML
- you require guaranteed profitability or financial advice
- you need a low-latency high-frequency trading system
- you want a no-code point-and-click trading platform

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, deep-learning, trading, data-science, workflow-automation
- domain: fintech, machine-learning, deep-learning, data-science
- platform: python, cross-platform
- tags: quantitative-trading, reinforcement-learning, backtesting, portfolio-allocation, stock-selection, algorithmic-trading, finrl, live-trading, alpaca, automation

## Member repositories
- AI4Finance-Foundation/FinRL-Trading (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:11.194025+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:33:50.425080+00:00, confidence not recorded.
  - readme: https://github.com/AI4Finance-Foundation/FinRL-Trading (fetched 2026-08-28T04:08:11.194025+00:00, sha 31aa364ad3a5)
  - homepage: https://ai4finance.org (fetched 2026-08-29T09:27:09.560554+00:00, sha d3d3e0581dfb)
  - site_page: https://ai4finance.org/about (fetched 2026-08-29T09:27:09.563026+00:00, sha 38823c8faa4a)
  - registry_pypi: https://pypi.org/pypi/finrl-trading/json (fetched 2026-08-29T09:27:09.564792+00:00, sha 1c439c64b876)
- Data as of 2026-08-30T08:39:29.467469+00:00.