cmunch1/nba-prediction
A project to deploy an online app that predicts the win probability for each NBA game every day. Demonstrates end-to-end Machine Learning deployment.
Builds gradient-boosted tree models (XGBoost/LightGBM) with probability calibration via scikit-learn's CalibratedClassifierCV to predict home team win likelihood from historical NBA stats. Automated pipelines using GitHub Actions daily scrape fresh game data via Selenium and BeautifulSoup, retrain models with Optuna hyperparameter tuning tracked in Neptune.ai, and serve predictions through a live Streamlit dashboard.
296 stars.
Stars
296
Forks
53
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cmunch1/nba-prediction"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
georgedouzas/sports-betting
Collection of sports betting AI tools.
roclark/sportsipy
A free sports API written for python
saccofrancesco/deepshot
AI model predicting NBA game outcomes using advanced stats and trends
NBA-Betting/NBA_Betting
Using data analytics and machine learning to create a comprehensive and profitable system for...
KengoA/fantasy-basketball
Scraping statistics, predicting NBA player performance with neural networks and boosting...