Qbot is an open-source, AI-oriented automated quantitative investment platform designed for individual traders and developers interested in quantitative finance. It provides a full-cycle workflow from data acquisition and strategy development to backtesting, simulated trading, and live automated trading, with a particular emphasis on leveraging machine learning and reinforcement learning for trading strategies.

How It Works

Qbot employs a modular, layered architecture separating data, strategy, and trading engine concerns. This design facilitates integration with diverse data sources and trading interfaces, enabling users to develop custom strategies and explore factor mining. It supports various trading paradigms, including supervised learning, market dynamics modeling, and reinforcement learning, aiming to enhance returns through AI-driven strategies and multi-factor models.

Quick Start & Requirements

• Install via git clone https://github.com/UFund-Me/Qbot --depth 1, then pip install -r dev/requirements.txt.
• Requires Python 3.8 or 3.9.
• Run with python main.py (or pythonw main.py on Mac).
• Detailed documentation is available at docs/Install_guide.md.

Highlighted Details

• Supports diverse trading objects: stocks, funds, futures, and cryptocurrencies.
• Integrates AI strategies (ML, RL, DL) and automated factor mining.
• Offers multiple trading modes: online backtesting, simulated trading, and live automated trading.
• Provides multi-channel notification options: email, Feishu, pop-ups, and WeChat.
• Features a comprehensive strategy pool with over 300 models from 40+ papers.

Maintenance & Community

The project is actively developed, with community contributions encouraged. Users can join discussions via GitHub or WeChat. The primary contact is Charmve.

Licensing & Compatibility

The project is licensed under CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International). This license restricts commercial use and requires derivative works to be shared under the same terms.

Limitations & Caveats

The project is primarily tested on Python 3.8 and 3.9; other versions are not guaranteed to work. The README advises against immediate live trading without thorough testing and states that the project's content does not constitute investment advice. The framework structure is noted as needing refinement.