AI-Stock-Master  by hengruiyun

AI-driven stock market analysis and investment decision support

Created 1 year ago
334 stars

Top 81.9% on SourcePulse

GitHubView on GitHub
Project Summary

AI Stock Master is an AI-driven platform designed for analyzing stock trends across Chinese, Hong Kong, and US markets. It targets investors seeking comprehensive decision support by integrating large language models with proprietary algorithms for multi-dimensional data interpretation. The platform aims to provide learning support and actionable insights through intelligent analysis and recommendation generation.

How It Works

This system employs a multi-layered analysis architecture built on AI theory, deep learning, and LLM technologies. It features an LLM-Driven Analysis Engine with integrated Mini Ollama for local, private processing, ensuring zero-configuration setup and data privacy. The core analytical components include the RTSI (Individual Stock Trend Strength Index) algorithm, which quantifies individual stock trend strength using modern portfolio theory and behavioral finance; the TMA (Technical Momentum Analysis) algorithm, designed for industry sector analysis and rotation opportunities; and the MSCI (Market Sentiment Composite Index) algorithm, which quantifies overall market sentiment through various indicators. These algorithms fuse multi-dimensional data and technical indicators to generate quantitative scores and AI-powered interpretations.

Quick Start & Requirements

  • Primary run command: AI-Stock-Master.bat
  • Prerequisites: Integration with Mini Ollama for local LLM runtime, designed for minimal memory footprint on desktop deployments. Specific hardware (GPU/CUDA) or Python version requirements are not detailed.
  • Demo link: TTfox.com

Highlighted Details

  • Core algorithms: RTSI (Individual Stock Trend Strength Index), TMA (Technical Momentum Analysis), and MSCI (Market Sentiment Composite Index).
  • LLM integration with Mini Ollama for local, private, and high-performance financial analysis.
  • TMA algorithm validation: Achieved a 12.3% annualized excess return over 5 years of historical backtesting.
  • Multi-layered analysis covering individual stocks, industries, and overall markets.

Maintenance & Community

  • Project Creator/Technical Support Contact: ttfox@ttfox.com
  • Developed in collaboration with TTFox.com.
  • No explicit community channels (e.g., Discord, Slack) or roadmap links are provided.

Licensing & Compatibility

  • The license type is not explicitly stated in the provided documentation.
  • Compatibility for commercial use or closed-source linking is undetermined due to the lack of licensing information.

Limitations & Caveats

The system is explicitly stated to be for programming learning purposes only and not for real investments. AI models are prone to prediction errors, and historical data does not guarantee future performance. Technical risks include potential model overfitting, algorithm failure under extreme market conditions, and sensitivity to data quality. Users are advised to combine AI analysis with their own judgment and risk tolerance.

Health Check
Last Commit

1 day ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
136 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.