Repolode
Submit
charliedream1

charliedream1/ai_quant_trade

A bilingual-docs collection of Python and Jupyter examples for AI-driven stock trading, covering learning materials, backtests, alpha mining, LLM stock forecasting and live-trading simulation.

View on GitHubWebsite
Stars
6,717
Forks
1,248
Open issues
4
Last commit
11 days ago

Repolode describes open-source projects and does not give investment advice. Trading and investing can lose money: assess the risk yourself and follow the laws where you live before using this project.

What is it?

AI Quantitative Trading Bot is a large collection of stock trading examples and learning material rather than a single installable trading engine. Each sub-project under egs_* is independent and comes with its own requirements.txt, covering traditional rule-based strategies such as double moving average backtests, reinforcement learning on the Dow Jones 30 via a FinRL tutorial, alpha mining with tsfresh, and sentiment analysis with StructBERT.

The repository also includes an LLM track for stock forecasting, including an Unsloth-based reasoning model training example, and an Excel-based A-share monitoring tool with alert thresholds, K-line charts and multiple data-source fallbacks. Several strategies are written for JoinQuant and can only run on that platform, and the live-trading simulation example relies on Wind software.

The project is aimed at learners and individual traders, and includes an awesome-style curated list of quant tools and frameworks, such as Qlib, Backtrader, Zipline and TA-Lib. Some advanced material and code are distributed through a paid knowledge community.

Key features

  • 01Traditional backtest examples such as double moving average strategy with plotted buy/sell points
  • 02Reinforcement learning trading tutorial based on FinRL
  • 03Automatic alpha mining with tsfresh and alpha libraries like alpha101 and TA-Lib
  • 04LLM-based stock forecasting training example using Unsloth
  • 05Excel stock monitor with price alerts, K-line charts and multi-source data fallback
  • 06Curated list of quant data sources, backtesting frameworks and tools

Use cases

  • Learning how a quantitative trading pipeline is structured from strategy to backtest
  • Experimenting with reinforcement learning or ML models on stock data
  • Monitoring A-share watchlists in Excel with alerts
  • Comparing quant frameworks and data sources before choosing one

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/charliedream1/ai_quant_trade.git
  2. 2

    Enter a project directory and install its dependencies

    cd egs_trade/vanilla/double_ma && pip install -r requirements.txt
  3. 3

    Follow that project's own README to get started

Things to know

  • The repo is not packaged as a Python package, and there is no root requirements file, so each example must be set up separately.
  • Apple Silicon users need to follow conda setup notes in each project's README.
  • Python 3.8+ on x86_64 is the stated baseline.

In collections

Reinforcement learning frameworks & training environments

Topics

#quant-trading#stock-trading#backtesting#reinforcement-learning#alpha-mining#pytorch#jupyter-notebook#trading-strategies#cpp#keras

FAQ

What is ai_quant_trade?
A bilingual-docs collection of Python and Jupyter examples for AI-driven stock trading, covering learning materials, backtests, alpha mining, LLM stock forecasting and live-trading simulation. AI Quantitative Trading Bot is a large collection of stock trading examples and learning material rather than a single installable trading engine. Each sub-project under egs_* is independent and comes with its own requirements.txt, covering traditional rule-based strategies such as double moving average backtests, reinforcement learning on the Dow Jones 30 via a FinRL tutorial, alpha mining with tsfresh, and sentiment analysis with StructBERT.
Is ai_quant_trade free to use? What license does it have?
ai_quant_trade is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is ai_quant_trade still maintained?
Actively maintained. The last commit to ai_quant_trade was on Oct 27, 2026.
What can I use ai_quant_trade for?
Learning how a quantitative trading pipeline is structured from strategy to backtest Experimenting with reinforcement learning or ML models on stock data Monitoring A-share watchlists in Excel with alerts Comparing quant frameworks and data sources before choosing one
How do I install ai_quant_trade?
Clone the repository: git clone https://github.com/charliedream1/ai_quant_trade.git Enter a project directory and install its dependencies: cd egs_trade/vanilla/double_ma && pip install -r requirements.txt Follow that project's own README to get started
Where can I get ai_quant_trade?
The source code and installation instructions are on GitHub: https://github.com/charliedream1/ai_quant_trade

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects