Reading the defense: How the NFL and AWS quantify coverage responsibility
Media Blog
The NFL and AWS developed an innovative AI framework called Coverage Responsibility to automatically determine defensive player assignments during football plays, addressing a long-standing analytics challenge.
- Used a spatial-temporal transformer architecture inspired by self-driving car technology
- Created three interconnected machine learning models to analyze:
- Coverage assignments
- Defender-receiver matchups
- Target defender identification
- Leveraged AWS services like SageMaker Studio, S3, and Amazon Bedrock for development
- Achieved 88% accuracy in predicting defensive responsibilities
- Enabled new analytics like ranking defenses by coverage disguise techniques
The project represents a significant advancement in football analytics, transforming how defensive strategies can be quantified and understood.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Sep 25
2025
2025
NFL Next Gen Stats and AWS decode defense coverage patterns
Sep 10
2024
2024
Beyond the box score: AWS and NFL AI-powered Tackle Analysis
Sep 10
2024
2024
A new take on tackling: NFL Next Gen Stats and AWS bring data to the gridiron
Feb 27
2025
2025
Inside the architecture: How the NFL delivers player performance insights at scale using Amazon QuickSight
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.