nshen7/alpha-gfn

A deep reinforcement learning framework for generating formulaic alpha factors for quantitative investment, powered by GFlowNet, implemented in Python&PyTorch.

43
/ 100
Emerging

This project helps quantitative traders and researchers automatically generate new mathematical formulas, called alpha factors, for predicting stock trends. It takes historical market data like prices and volumes, and outputs diverse formulas that signal potential buying or selling opportunities. Quantitative investment professionals can use these formulas to inspire new trading strategies or integrate them directly into existing ones.

104 stars.

Use this if you are a quantitative trader or researcher looking for an automated way to discover novel alpha factors for stock trend prediction.

Not ideal if you need to analyze non-technical indicators or market data beyond daily frequency, as this demo focuses solely on technical indicators and daily data.

quantitative-investment alpha-factor-research algorithmic-trading financial-modeling market-prediction
No License No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

104

Forks

16

Language

Jupyter Notebook

License

Last pushed

Jan 23, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nshen7/alpha-gfn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.