thadhutch/sports-quant

End-to-end NFL data pipeline that scrapes PFF grades and Pro Football Reference game data, builds analysis-ready datasets, and trains ensemble XGBoost models with walk-forward backtesting

49
/ 100
Emerging

This project helps sports bettors and enthusiasts predict outcomes for March Madness and NFL games. It takes historical game data and team performance metrics, then generates predictions for March Madness brackets, including upset calls and survivor pool picks, and NFL over/under bets. It's designed for anyone looking for data-driven insights to improve their sports betting strategy or simply better predict game results.

Available on PyPI.

Use this if you want to make more informed predictions for March Madness tournament brackets or NFL over/under bets based on advanced statistical models.

Not ideal if you're looking for predictions for sports other than college basketball (March Madness) or NFL football, or if you prefer purely subjective, gut-feeling betting.

sports-betting NFL-analytics March-Madness-prediction sports-modeling gambling-strategy
Maintenance 13 / 25
Adoption 5 / 25
Maturity 25 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

MIT

Last pushed

Mar 18, 2026

Commits (30d)

0

Dependencies

16

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/data-engineering/thadhutch/sports-quant"

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