Zizhao-HUANG

Zizhao-HUANG / FullStackAutoQuant

Public

Production-grade end-to-end automated quantitative trading system

algorithmic-trading automated-trading backtesting deep-learning python
18
0
100% credibility
Found Feb 22, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

FullStackAutoQuant is a complete automated quantitative trading system that handles market data, AI predictions, backtesting, risk controls, and live execution through a user-friendly web dashboard.

How It Works

1
🔍 Discover Smart Stock Picker

You hear about a helpful tool that uses smart math to suggest the best stocks each day, like having a personal trading advisor.

2
📱 Set Up Your Accounts

Connect your trading account and data source with a few simple clicks, so the tool knows your stocks and market info.

3
🧠 Get Daily Stock Ideas

The tool crunches numbers overnight and shows you top stock picks with confidence scores, ready for the trading day.

4
📊 Test Your Ideas Safely

Run pretend trades on past data to see how the picks would have performed, building trust before real money.

5
🚀 Start Live Trading

Review the plan, adjust if needed, and let it place trades automatically with built-in safety checks.

📈 Grow Your Portfolio

Watch your investments perform with daily oversight, risk controls, and easy tweaks via the friendly dashboard.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 11 to 18 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is FullStackAutoQuant?

FullStackAutoQuant is a production-grade end-to-end automated quantitative trading system in Python that handles everything from market data ingestion to live trade execution. Built on Qlib for data handling, PyTorch for deep learning models, and Streamlit for a web dashboard, it delivers ranked stock signals, backtesting with realistic costs, and API-driven trading for A-shares like CSI300. Users get a ready-to-run pipeline that spits out daily signals and portfolio oversight without piecing together disparate tools.

Why is it gaining traction?

Unlike fragmented open-source quant projects that tackle just modeling or backtesting, this stands out as a cohesive, production-grade system with built-in risk controls, uncertainty estimation via MC dropout, and automated scheduling. Developers dig the one-command setup for inference, backtests, and live runs via JoinQuant or GM Trade APIs, plus verifiable performance like 16.7% annualized excess return on CSI300. The Streamlit UI for manual overrides hooks those testing strategies in real markets.

Who should use this?

Python quant devs or algo traders targeting Chinese A-shares who want an automated, fullstackautoquant pipeline without reinventing data pipelines or execution logic. Ideal for researchers validating models on CSI300 or funds prototyping live strategies with position limits and drawdown halts.

Verdict

Grab it if you're in quant trading and need a Python-based production-grade starter—solid docs, Makefile workflows, and pre-trained weights make it approachable despite 17 stars and 1.0% credibility score signaling early maturity. Test coverage and CI are in place, but expect tweaks for your broker.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.