What is it about?

Sport analytics has proven to be very effective in analyzing performance on player and team level alike. This notion applies for tactical elements as well, where most of the literature focuses on describing the events taking place on the court, but only limited research explores alternative options how plays could have turned out. Our paper aims to narrow this gap by characterizing the defensive formations that allow an offensive player to timely cut to the basket while a teammate is driving. Using positional data from the NBA, we created a model that detects the possiblities for such a cut in any given moment of a drive. The impacts of the individual features, along with their interactions, led us to the conclusion that the observation of a few key attributes of defender behavior makes it possible to recognize openings in the defense.

Featured Image

Why is it important?

The approach demonstrates that abstract and complex tactical situations of chaotic sport games can be broken down to quantifiable components. Such features can help coaching teams in designing specific drills for the practice as well as developing systems to automatically detect, count and analyze game situations that had the potential to play out in a different way.


We created our model using only geometrical attributes. As technology progresses, many other aspects will be available to include as features – making the topic even more exciting in the upcoming years for basically any team sport.

Bence Supola
Universitat Wien

Read the Original

This page is a summary of: Modeling the formation of defensive gaps in basketball: Cutting on a teammate’s drive, PLoS ONE, February 2023, PLOS,
DOI: 10.1371/journal.pone.0281467.
You can read the full text:

Open access logo


The following have contributed to this page