Super Bowl Sunday is upon us and fans of both the Los Angeles Rams and Cincinnati Bengals are eager to see which team comes out on top.
This week, the NFL and Amazon Web Services (AWS) released tons of statistics through Next Gen Stats (NGS) to show how each team made it to the championship game. One of their newest statistics -- called "Passing Score" -- turned out to be one of the most accurate predictors of success this season.
The NFL and AWS told ZDNet that the statistic assesses whether a quarterback made the optimal decision after the play. Dozens of quarterback evaluation metrics exist but they all miss out on isolating the specific variables a quarterback must evaluate before a passing play, the NFL explained.
To illustrate the statistic's accuracy, AWS ranked the performances of quarterbacks in 2021, finding that Aaron Rodgers, Joe Burrow, and Matthew Stafford were the only players with scores above 90.
On Thursday, Rodgers won the MVP award and Burrow is facing Stafford in the Super Bowl today. 13 of the top 15 quarterbacks by NGS Passing Score made the playoffs, and the two that didn't -- Justin Hebert and Matt Ryan -- were in the hunt until the final weeks of the season.
Mike North, vice president of broadcast for the NFL, told ZDNet the NGS Passing Score shows remarkable parity between Burrow and Stafford.
"Both have shown ability to sustain drives, be efficient and effective passers, and make stellar plays in the final minutes of the games," North said. "While our models don't predict the winner, we can say there is a high probability of excellent quarterback play in the Super Bowl."
Stafford ranked second in the league in total pass EPA on attempts while Burrow ranked fourth. Both had exceptional Conference Championship games that included spectacular individual performances from each.
NGS said the Kansas City Chiefs' Chris Jones was within two yards of Burrow for 4.3 straight seconds but failed to take him down on a crucial third down in the 4th quarter. Stafford was pressured on a season-high 38.3% of his dropbacks but took advantage when he was kept clean, completing 24 of 29 passes for 254 yards and 2 TD, according to NGS.
"There are a lot of factors that determine who makes the Super Bowl, but intuitively it makes sense that the best performing quarterbacks are the ones playing in the Super Bowl. NGS goes beyond intuition to quantify the contributions of a quarterback from the team's collective passing production and efficiency," North explained.
"Instead of simply evaluating a quarterback on his passing yards, touchdowns, and interceptions, the NGS Passing Score equation leverages the outputs of our models to better evaluate passing performance relative to a league-average, isolate the factors that the quarterback can control, represent the most indicative features of winning football games, and encompass passing performance in a single composite score (ranging from 50 to 99)."
Josh Helmrich, NFL director of strategy and business development, said they spent over a year developing the components that make up the Next Gen Stats Passing Score.
"Machine learning technology helps to deliver insights never before possible, and we believe the Next Gen Stats Passing Score is the next great example of that. We know it will help fans better understand and engage with the game," Helmrich said.
NGS also released dozens of other statistics laying out the case for each team, highlighting star players from each squad like Aaron Donald, Trey Hendrickson, Cooper Kupp, Ja'Marr Chase, Chidobe Awuzie, Von Miller and more.