An Investigation of Three-point Shooting through an Analysis of NBA Player Tracking Data
Bradley A. Sliz

TL;DR
This paper uses NBA player tracking data and statistical analysis to evaluate the impact of team strategies on three-point shot success, highlighting teamwork's importance and identifying effective shooters.
Contribution
It introduces a novel method combining player tracking data with variable importance algorithms to measure strategy influence and player shooting propensity.
Findings
Teamwork strategies significantly impact three-point success
Player tracking features can identify effective and under-utilized shooters
Advanced analysis reveals insights not possible three years ago
Abstract
I address the difficult challenge of measuring the relative influence of competing basketball game strategies, and I apply my analysis to plays resulting in three-point shots. I use a glut of SportVU player tracking data from over 600 NBA games to derive custom position-based features that capture tangible game strategies from game-play data, such as teamwork, player matchups, and on-ball defender distances. Then, I demonstrate statistical methods for measuring the relative importance of any given basketball strategy. In doing so, I highlight the high importance of teamwork based strategies in affecting three-point shot success. By coupling SportVU data with an advanced variable importance algorithm I am able to extract meaningful results that would have been impossible to achieve even 3 years ago. Further, I demonstrate how player-tracking based features can be used to measure the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSports Analytics and Performance · Sports Performance and Training
