{"repo":"Zizhao-HUANG/FullStackAutoQuant","free":true,"listed":false,"github":"https://github.com/Zizhao-HUANG/FullStackAutoQuant","clone":"git clone https://github.com/Zizhao-HUANG/FullStackAutoQuant.git","description":"Production grade end to end automated quantitative trading system.","language":"Python","stars":21,"topics":["algorithmic-trading","backtesting","python","quantitative-finance","automated-trading","deep-learning","pytorch"],"license":null,"category":"trading","readme_excerpt":"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 Live Trading Signal to order execution via JoinQuant/GM Trade API with automated daily scheduling Backtesting Engine Full simulator with NAV tracking, transaction costs, and standard performance metrics WebUI Dashboard Streamlit interface for portfolio oversight, manual overrides, and one click operations Model TCN LocalAttention GRU A hybrid deep learning architecture ( 180K parameters) designed for cross sectional stock rankin","default_branch":null,"files":null,"tree":[],"storefront":"/r/Zizhao-HUANG","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Zizhao-HUANG/FullStackAutoQuant/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}