NFL on AWS
The NFL uses the power of AWS Machine Learning to create a better experience for fans, players, and teams.
AWS + Next Gen Stats Unveil New Pressure Probability Stat
Anatomy of Pressure
Leveraging concepts from the 2023 Big Data Bowl, see how AWS engineers trained a series of ML models on more than 90,000 passing plays over the last 5 years to better capture QB pressure and how it evolves over the course of a dropback.
How AWS is powering the NFL
Big Data Bowl
"A global data science competition that looks to address unanswered football questions. Over the last 5 years, more than 15 Next Gen Stats started as Big Data Bowl submissions."
- Mike Lopez
Sr. Director of Data and Analytics - NFL
Next Gen Stats
“The AWS ML teams bring solutions and techniques that we've never seen before and, combined with our football expertise and experience productionizing stats, we continue to have success every time we create a new metric.”
- Mike Band
Next Gen Stats
Seattle Seahawks
“Data is only increasing. So, putting systems in place to handle this data is critical to stay on the cutting edge of player analytics.”
- Patrick Ward
Head of Research and Analytics - Seattle Seahawks
Player Health & Safety
“Our end goal is to be able to predict and prevent injuries working with AWS."
- Jennifer Langton
SVP of Health and Safety Innovation - NFL
How AWS is powering the NFL
Big Data Bowl
"A global data science competition that looks to address unanswered football questions. Over the last 5 years, more than 15 Next Gen Stats started as Big Data Bowl submissions."
- Mike Lopez
Sr. Director of Data and Analytics - NFL
Next Gen Stats
“The AWS ML teams bring solutions and techniques that we've never seen before and, combined with our football expertise and experience productionizing stats, we continue to have success every time we create a new metric.”
- Mike Band
Next Gen Stats
Seattle Seahawks
“Data is only increasing. So, putting systems in place to handle this data is critical to stay on the cutting edge of player analytics.”
- Patrick Ward
Head of Research and Analytics - Seattle Seahawks
Player Health & Safety
“Our end goal is to be able to predict and prevent injuries working with AWS."
- Jennifer Langton
SVP of Health and Safety Innovation - NFL
Why the NFL chooses AWS
AWS is conducting the majority of Machine Learning (ML) being done in the cloud today. The NFL uses the power of AWS ML to create new stats and improving player health and safety, while creating a better experience for fans, players, and teams, all in real time.
Machine Learning
The NFL uses AWS machine learning and data analytics services boost the accuracy, speed, and insights for Next Gen Stats and Player Health and Safety.
Data Dashboards
The NFL uses Amazon QuickSight to organize and analyze real-time data captured during games.
Flexible Compute
The NFL uses thousands of Amazon EC2 Spot Instances to save millions of dollars and thousands of hours when building the annual season schedule.
Applying machine learning to data
By leveraging AWS’s broad range of cloud-based Machine Learning capabilities, the NFL is taking game-day to the next level—so that fans, broadcasters, coaches, and teams can benefit from deeper insights. Training data from traditional box score statistics runs through hundreds of processes within seconds with the output fed into Amazon SageMaker. These models are used in real-time during games to generate outputs such as formations, routes, and events.
AWS Services Powering Next Gen Stats
See How the NFL Engages AWS
The league has built several Machine Learning stats on AWS, each of which relies on different data points. Here are just a few examples. To see more, visit nextgenstats.nfl.com
Passing Score
A first-of-its-kind AI tool that combine seven ML models, including a new model to predict the value of a pass before the ball is thrown, to evaluate quarterback passing performance.
4th Down Decision Guide
Uses Amazon SageMaker to analyze win probability, which informs how the game will change based on hypothetical outcomes, and conversion probability, which predicts if the offense will convert a fourth down or 2-point conversion.
Completion Probability
This predictive model uses Amazon SageMaker to compute the probability that any given pass will be completed based on the distance of the pass, the receiver’s separation from the nearest defender, his spot on the field, the amount of pressure on a QB, and more.
Expected Rushing Yards
This metric uses Amazon SageMaker to predict how many rushing yards a ball-carrier is expected to gain on a given carry based on the relative location, speed, and direction of blockers and defenders.
Expected Return Yards
The newest advanced ML-powered stat from AWS and the NFL tackles the hidden dynamics of punt and kickoff returns.
Coverage Classification
Coverage Classification is a first-of-its-kind AI system that can identify 8 different types of man and zone defensive coverages just seconds after the play ends. Trained on over 60,000 NFL plays over the last 4 seasons, it uses player tracking data to factor in variables like initial defensive player alignment, how they adjust to offensive players moving once the ball is snapped, player acceleration, disguised coverages, and even blown coverage assignments to determine which coverage was used.
Learn how other enterprises are transforming their business with the power of AWS.