Football · Research

NFL Gravity Metric

Active2025-26Updated Aug 6, 2026
Project Overview

A pass-rusher gravity metric that measures observed blocker attention during true pass sets, models expected attention from Big Data Bowl tracking features, and ranks defenders by the extra attention they command.

Problem & Objective

Traditional pass-rush production can miss defenders who create value by occupying extra blockers and opening cleaner rush lanes for teammates.

Analytical Approach

The team defines observed attention from blocker-to-rusher matchups using a weighted distance and orientation metric, then models expected attention with engineered features and graph-based spatial concepts.

Key Result & Impact

Initial XGBoost modeling explains meaningful variance in expected attention and surfaces case studies like Grady Jarrett, whose blocker attention exceeds what conventional production suggests.

Tech Stack & Tools
PythonXGBoostGNNKaggle