fischlerben/NBA-Position-Predictor

Machine Learning project using 15 seasons of NBA data (2005-2020) to predict player position. Decision Trees, Random Forests, Support Vector Machines (SVMs) and Gradient Boosted Trees (GBTs) utilized. Example PCA transformation of X-data included as well. Specific predictions made at the end, leading to interesting insights into what players are out-of-position.

26
/ 100
Experimental

This project helps basketball analysts, coaches, or scouts understand player roles by predicting an NBA player's position based on their per-36-minute statistics over multiple seasons. You input a player's statistical profile, and it outputs their most probable position, highlighting if their stats deviate from typical position norms. This helps identify players who might be playing out of position or have unique skill sets.

No commits in the last 6 months.

Use this if you want to analyze NBA player statistics to understand positional archetypes and identify players whose on-court performance suggests they might be more suited for a different role.

Not ideal if you need to predict player performance, game outcomes, or analyze team strategies, as it focuses solely on positional classification.

NBA-analytics player-scouting sports-statistics basketball-strategy player-evaluation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

Jupyter Notebook

License

Last pushed

Feb 09, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/fischlerben/NBA-Position-Predictor"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.