FALL 2023
Optimal Strategy for Defensive Pressure in American Football: Insights from an Expected Sack Model
AUTHOR
Tej Seth, University of Michigan
ABSTRACT
The impact of a defender getting to the quarterback and recording a sack is a critical outcome in American football. However, limited research has been conducted on the positioning of defenders that could potentially increase their chance of success. In this study, we utilize a combination of Pro Football Focus charting data and NFL Next Gen Stats tracking data to create the probability of a defender recording a sack based on their X and Y coordinate alignment, listed position, offensive and defensive formations and game situation information. The data analyzed includes weeks 1 through 8 of the 2021 NFL season, as provided by the league through the 2022 Big Data Bowl competition. An eXtreme Gradient Boosted Classifier was used to predict the probability of a defender documenting a sack on a given play. The findings reveal that distance from the quarterback is the most influential factor, with defenders in closer proximity to the opposition being more likely to penetrate the backfield. Additionally, a player’s roster position label emerged as a significant variable, with cornerbacks generally having lower odds of recording sacks compared to outside linebackers. These results suggest that certain teams, such as the Cincinnati Bengals, may strategically position their defenders in more optimal spots for sacking the quarterback compared to teams like the Atlanta Falcons.
About the Wharton Sports Analytics Journal
ISSN 3070-4065 (Online)
The Journal is published by the Wharton Sports Analytics and Business Initiative and features original student research at the intersection of sports, business, and analytics. Explore the Journal.

