Defensive Player Classification in the National Basketball Association

TL;DR

This paper introduces a novel method for classifying NBA players into five defensive types using advanced defensive metrics and Gaussian Mixture Models, improving understanding of player roles beyond traditional physical attributes.

Contribution

It presents a new classification approach leveraging high-quality defensive metrics and GMM to identify distinct defensive player types in the NBA.

Findings

Five defensive player types identified

GMM effectively determines optimal number of clusters

Enhanced understanding of defensive roles in basketball

Abstract

The National Basketball Association(NBA) has expanded their data gathering and have heavily invested in new technologies to gather advanced performance metrics on players. This expanded data set allows analysts to use unique performance metrics in models to estimate and classify player performance. Instead of grouping players together based on physical attributes and positions played, analysts can group together players that play similar to each other based on these tracked metrics. Existing methods for player classification have typically used offensive metrics for clustering [1]. There have been attempts to classify players using past defensive metrics, but the lack of quality metrics has not produced promising results. The classifications presented in the paper use newly introduced defensive metrics to find different defensive positions for each player. Without knowing the number of categories that players can be cast into, Gaussian Mixture Models (GMM) can be applied to find the optimal number of clusters. In the model presented, five different defensive player types can be identified.