# kyleskom/NBA-Machine-Learning-Sports-Betting

NBA sports betting using machine learning

Repository: https://github.com/kyleskom/NBA-Machine-Learning-Sports-Betting
Canonical: https://ross.abutalabs.com/products/nba-machine-learning-sports-betting
Language: Python
License Family: other
Topics: python, tensorflow, keras, nba, nba-analytics, nba-prediction, sports-betting, sports, sports-analytics, data-science, machine-learning, gambling, sports-data, deep-learning, neural-network, ai, gpt, llm
Last push: 2026-01-09T02:04:03+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 61, release rhythm 53, longevity 100
- inputs: {"age_days": 2469, "days_push": 237, "days_rel": 237, "gap_med": 74, "n_releases_24m": 4}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1696, forks 567 (observed 2026-08-28T04:05:23.929659+00:00)

## What it is
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
- artifact type: application
- maturity: active
- function: machine-learning, deep-learning, data-science, etl, web-scraping
- domain: machine-learning, data-science, sports
- platform: python, cli, cross-platform
- tags: sports-betting, nba, xgboost, neural-networks, kelly-criterion, odds-prediction, flask, gambling

## Member repositories
- kyleskom/NBA-Machine-Learning-Sports-Betting (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:23.929659+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:37:54.162847+00:00, confidence not recorded.
  - readme: https://github.com/kyleskom/NBA-Machine-Learning-Sports-Betting (fetched 2026-08-28T04:05:23.929659+00:00, sha 3ae6f19feceb)
- Data as of 2026-08-30T08:39:29.467469+00:00.