2 files

Clustering NBA Players Based on Offensive and Defense Skillset

posted on 11.05.2021, 21:08 by Ashwin Raj
This visualization, titled "Clustering NBA Players Based on Offensive and Defense Skillset" was submitted by Ashwin Raj to the University of Arizona Libraries 2021 Data Visualization Challenge. It received the third place win within the undergraduate classification.

Submitted Abstract:
This project uses 2019 NBA Player data from basketball-reference to cluster NBA players into roles based on their offensive and defensive skillsets. Using 3-pointers made as the offensive metric and steals as the defensive metric, and then standardizing these metrics per 36 minutes, players were clustered as Low-Impact, Bench Defense, Bench Offense, Shooters, Two-Way, and Elite. Teams can use this data about their players to determine rotations, offensive & defensive strategy, and even potential trades. The cluster analysis was done using K-Means with k=6, and the interactive plot was created using GGPlot and Plotly.

For inquiries regarding the contents of this dataset, please contact the Corresponding Author listed in the README.txt file. Administrative inquiries (e.g., removal requests, trouble downloading, etc.) can be directed to data-management@arizona.edu


Usage metrics

University Libraries