v1.0.0 - Initial Public Release

NBA AI v1.0.0

NBA game prediction system with automated daily pipeline, multiple prediction engines, and web dashboard.

What's Included

In the repo:

• Full source code (data collection, prediction pipeline, web app)
• Trained models: Baseline, Linear (Ridge), Tree (XGBoost), MLP (PyTorch)
• Ensemble predictor combining all four models

In this release (download below):

• NBA_AI_starter.sqlite.gz (88 MB) — Current season database with games, box scores, play-by-play, betting lines, injury reports, and predictions. Extract to data/NBA_AI_starter.sqlite.

Quick Start

See the README for full setup instructions.

git clone https://github.com/NBA-Betting/NBA_AI.git
cd NBA_AI
python -m venv venv && source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env

Download NBA_AI_starter.sqlite.gz from below and extract:

python -c "import gzip, shutil; shutil.copyfileobj(gzip.open('NBA_AI_starter.sqlite.gz','rb'), open('data/NBA_AI_starter.sqlite','wb'))"

Run the web app:

python start_app.py

Notes

• Deep learning models (Phase5, Phase3) are not included due to size. Train your own with scripts in scripts/.
• The pipeline backfills missing games automatically on first run (may take 10-30+ minutes).
• The web app reads from the database only — run the pipeline to collect new data.

---

This is a personal side project provided "as is" with no guarantees of quality, functionality, or ongoing maintenance.