An open-source Python quantitative trading system supporting stocks, options, futures, and cryptocurrencies with integrated machine learning.
Abu is an open-source quantitative trading system written in Python that provides a framework for developing, testing, and deploying algorithmic trading strategies. It solves the problem of complex, code-intensive quantitative analysis by integrating traditional technical analysis with machine learning to optimize strategies for stocks, options, futures, and cryptocurrencies.
Quantitative traders, algorithmic developers, and investors interested in backtesting and automating strategies across global equity, derivatives, and digital currency markets using Python.
Developers choose Abu for its comprehensive integration of hundreds of technical analysis models and AI-driven optimization in a single open-source framework, enabling strategy development without relying on expensive proprietary platforms.
阿布量化交易系统(股票,期权,期货,比特币,机器学习) 基于python的开源量化交易,量化投资架构
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Supports backtesting and live trading across A-shares, US stocks, Hong Kong stocks, futures, options, Bitcoin, and Litecoin, as detailed in the Key Features, enabling diverse strategy testing.
Employs machine learning with physical, dopamine-based biological, and quantitative pattern model groups to intelligently optimize strategies, improving live trading performance based on the framework's AI systems.
Combines hundreds of sub-models from Elliott Wave Theory, Chan Theory, harmonic patterns, chart formations, and more, providing a comprehensive toolkit for quantitative analysis.
Utilizes 18,496 quantified buy/sell signal strategies derived from self-learning and evolutionary processes, offering a wide range of pre-built strategies for immediate use.
Requires Anaconda for Python environment deployment and has multiple dependencies, as noted in the installation section, which can be cumbersome for quick experimentation.
Much of the README, tutorials, and resources are in Chinese, with limited English translation, hindering accessibility for global developers unfamiliar with the language.
The vast array of integrated models, AI systems, and 18,000+ strategies can be daunting and opaque, making it difficult for users to understand or customize core logic without deep diving.
AI systems like 'dopamine-based biological models' are described abstractly in the README, lacking transparency and potentially acting as a black box for strategy optimization.