kyleskom/NBA-Machine-Learning-Sports-Betting

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1696 stars · 567 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python application that predicts NBA game winners and totals (over/under) using XGBoost and neural network models trained on historical team stats and sportsbook odds. It includes a data collection pipeline, model training scripts, a CLI for daily predictions with expected value and Kelly Criterion sizing, and a Flask web app for browsing outputs.

Use cases

• predict NBA game winners with machine learning
• predict NBA over/under totals
• calculate expected value for sports bets
• compute Kelly Criterion stake sizing
• scrape NBA team stats and sportsbook odds
• train models on historical NBA game data

When to choose

• you want ready-made ML models for NBA moneyline and totals predictions
• you want an end-to-end pipeline from data scraping to daily predictions
• you want expected value and Kelly Criterion bankroll guidance for NBA bets

When to avoid

• you need predictions for sports other than the NBA
• you need a guaranteed profitable betting system - model outputs are probabilistic estimates
• you need a production web service - the Flask app is a simple browsing interface
• you require a maintained library with a license - the repo has no license

Facets

application · maturity active

machine-learning deep-learning data-science etl web-scraping machine-learning data-science sports python cli cross-platform sports-betting nba xgboost neural-networks kelly-criterion odds-prediction flask gambling

Member repositories

For agents

markdown · JSON · MCP: product_card(name="kyleskom/NBA-Machine-Learning-Sports-Betting")