FullStackAutoQuant
Unverified ML strategy on Multi by Lyahn-Huang. BotFinder score 18 out of 100.
Production grade end to end automated quantitative trading system.
Source: github
BotFinder analysis pending.
FullStackAutoQuant
FullStackAutoQuant End to End Deep Learning Quantitative Trading System --- FullStackAutoQuant is a production grade, fully automated quantitative trading system that covers the entire pipeline from raw market data ingestion to live trade execution. Unlike most open source quant projects that focus on a single component (model OR backtesting OR execution), this system integrates all stages into a cohesive, automated pipeline. Architecture Key Features | Module | What it does | |--------|-------------| | Data Pipeline | Automated data updates via Tushare (lightweight) or Docker/Dolt (full history), custom factor synthesis (Alpha158 + 2 proprietary factors), and feature matrix construction | | Deep Learning Model | Proprietary TCN Attention GRU architecture with strict temporal causality for cross sectional stock ranking | | Uncertainty Estimation | MC Dropout (16 pass) produces per stock confidence scores; low confidence signals are filtered before trading | | Risk Management | Multilayer controls: max drawdown limits, limit state filtering, position caps, and confidence thresholds |
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)