live
01
NFL Nostradamus
See the game before it's played.
NFL Nostradamus is a full-stack machine learning application that predicts NFL game winners and point spreads using 20 seasons of play-by-play data. The classifier achieves 62.89% validation accuracy on the 2023 season — beating both home-team and better-record baselines — using a temporally split XGBoost pipeline that eliminates data leakage common in hobby ML projects. The spread regression model extends predictions beyond win/loss into point differential territory, all served through a FastAPI backend, persisted in PostgreSQL, and rendered in a live React dashboard.
62.89% accuracy+4.7pp over baseline20 seasons of data
Back to projects