# TradeMaster-NTU/TradeMaster

TradeMaster is an open-source platform for quantitative trading empowered by reinforcement learning :fire: :zap: :rainbow:

Repository: https://github.com/TradeMaster-NTU/TradeMaster
Canonical: https://ross.abutalabs.com/products/trademaster
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: finance, fintech, pytorch, reinforcement-learning, stock-market, trading-platform, machine-learning, investment-strategies, jupyter-notebook, python, quantitative-trading
Last push: 2025-06-04T03:57:56+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 25, release rhythm 8, longevity 100
- inputs: {"age_days": 1471, "days_push": 455, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3050, forks 557 (observed 2026-08-28T04:07:39.579712+00:00)

## What it is
TradeMaster is an open-source Python platform for quantitative trading powered by reinforcement learning, covering the full pipeline of algorithm design, implementation, evaluation, and deployment. It is built on PyTorch and distributed under the Apache-2.0 license.

## Use cases
- backtest RL trading strategies on stock market data
- train deep reinforcement learning agents for quantitative trading
- evaluate and compare trading algorithms
- research RL-based investment strategies
- deploy RL trading models in a full pipeline

## When to choose
- you want to apply reinforcement learning to quantitative trading research
- you need an end-to-end pipeline for designing, evaluating, and deploying RL trading algorithms
- you work in Python with PyTorch and finance data

## When to avoid
- you need a production low-latency live trading execution system
- you want a no-code or GUI trading platform
- you are not working in Python

## Facets
- artifact type: library
- maturity: active
- function: reinforcement-learning, machine-learning, trading, data-science
- domain: fintech, machine-learning, reinforcement-learning
- platform: python, windows
- tags: quantitative-trading, finance, pytorch, algorithmic-trading, backtesting, stock-market, linux, macos

## Member repositories
- TradeMaster-NTU/TradeMaster (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:39.579712+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 2026-08-29T18:46:49.988271+00:00, confidence not recorded.
  - readme: https://github.com/TradeMaster-NTU/TradeMaster (fetched 2026-08-28T04:07:39.579712+00:00, sha cd70d7de3a6e)
- Data as of 2026-08-30T08:39:29.467469+00:00.