The NFL and Amazon Web Services (AWS) unveiled a new stat this week to help rank the league’s most prolific quarterbacks based on their decision making.

The team behind Next Gen Stats (NGS) created the “Passing Score” statistic to assess whether a quarterback made the optimal decision after the play. quarterbacks, but they all fail to isolate the specific variables a quarterback must assess before a passing play.

Josh Helmrich, director of strategy and business development for the NFL, said ZDNet that AWS and the NFL worked together to combine 7 different machine learning models and multiple game variables to create the Next Gen Stats Passing Score.

“With the NFL playoffs fast approaching, we want to provide fans with deeper analysis, more context and additional ways to understand one of the most important positions in sports – the quarterback of This new metric will help fans better understand the quarterback’s passing performance, relative to his decision, on every play,” Helmrich said.

“The quarterback position is much more complex than just the outcome of the game. To help understand quarterback decision-making and all the variables associated with it, we have spent over a year developing the components that make up the Next Gen Stats Passing Score.

In a blog post, AWS and the NFL explained that quarterbacks make hundreds of split-second decisions based on how the defense is lined up, how much time is left in the game, and the yards needed for a first down or a touchdown.

To illustrate the accuracy of the stat, AWS ranked quarterback performance in 2021, finding that Aaron Rodgers, Joe Burrow and Matthew Stafford were the only players with scores over 90. Ryan Tannehill, Patrick Mahomes, Josh Allen and Tom Brady weren’t far behind with scores above 88.

Dak Prescott, Kyler Murray and Jimmy Garoppolo all had 87. Jalen Hurts, Derek Carr and Mac Jones had scores above 82. Ben Roethlisberger was 14th on the list with a 70 and is the only quarterback in the last four seasons qualify for the playoffs with a score below 82.

Despite hundreds of variables affecting the outcome of a game, statistical credit or blame always goes to the quarterback. Priya Ponnapalli of AWS ML Solutions Lab said ZDNet the machine learning technology and data analysis tools used to create the passing score will help viewers understand the game and the decisions made by the quarterbacks.

“NGS spent nearly a year solving a series of complex technological problems to create the Passing Score tool,” AWS explained.

“Building on years of building and deploying machine learning (ML) models powered by AWS, the NGS engineering and analytics team worked with the AWS Professional Services data science group to optimize and combine seven ML models, including a new model to predict the value of a pass before the ball is thrown. The combined ML models feed into the new NGS pass score. Each individual model provides compelling information about what is happening on the field, such as expected yards and probability of completion. By combining the models, a score (a number between 50-99) better reflects the intuition used by fans, coaches and players to assess the performance of pass from a quarterback.”

Ponnapalli and AWS explained that the new stat isolates the passer’s contribution to the outcome of a passing game, independent of the receiver, and controls the difficulty level of each pass.

Passing Score is calculated using tracking data to predict how many yards a receiver will gain if targeted, combined with an improved completion probability model, which can now also estimate the probability of an interception.

AWS noted that in the future, Passing Score may expand to take into account other elements such as rushers, sacks, and pressures.

“Machine learning technology is helping to deliver insights never before possible, and we believe the Next Gen Stats Passing Score is the next great example of that,” Helmrich said. “We know this will help fans better understand and engage with the game.”