- BYU graduate students and a UVU grad won the NFL's Big Data Bowl, a competition showcasing analytics research.
- Their model analyzed player-tracking data to show how a defensive back can move once the football has left a quarterback's hand.
- The team won $9,000 and redemption, after an unsuccessful attempt the year prior.
PROVO — While Brigham Young University is no stranger to the NFL scouting combine, it's usually only athletes vying for the attention of teams.
That changed this year, when a group of BYU graduate students and a Utah Valley University graduate took the trip to Indianapolis, Indiana, last week.
Not to run the 40-yard dash, but to present their research findings to league executives at the NFL's annual Big Data Bowl — the league's premier analytics competition — as one of only five winning groups across the nation.
The team, comprised of BYU graduate students Grant Nielson, Connor Thompson and Evan Miller, alongside UVU graduate Evan West, decided to look into something every football fan probably thinks on any given Saturday or Sunday: "Why didn't that defender react sooner to make a play on the football?"
To get to the bottom of that question, the team analyzed player-tracking data to determine what defenders can and cannot do in the split second between the quarterback's release and the receiver's catch point.
"We answer the question of what a cornerback or a defensive back could have done and what would have happened if he had done things differently," Thompson said in a release. "If you think he should have jumped the route, our computations show where he could have gone and the probability that he could have gotten an interception. Data. Not just vibes."
The panel the group presented their research to included Greg Olsen, a former NFL player of 14 years and current broadcaster, as well as the NFL's chief data and analytics officer, Paul Ballew, and Amazon Web Services executives.
If you've kept up with trends in modern football, you'll know all about the analytics and data renaissance that the league has seen over the past decade or so.
It's not exclusive to the teams, either, with the NFL integrating it into the fan experience in myriad ways. The newly launched NFL IQ lets fans get a front-row seat into an NFL offseason to see how roster construction really works.
For a few years now, Amazon's broadcast of Thursday Night Football has featured "Prime Vision," giving the casual viewer a new depth and level of understanding than a regular broadcast by mixing advanced stats and on-field graphics that can show anything from ballcarrier speed to what defenders are likely to be blitzing on a crucial third down.
This trend, which is more entrenched at this point, wasn't lost on the research team.
"This is something that's going to move the game we love forward," Nielson said in a release. "Millions of people care about the NFL, and this matters to the NFL as a whole. And I realized, 'Me and my friends are a critical part of that, at least for the next hour.'"
The team's model translates tracking data points to show the realistic options a defender actually has once the ball leaves the quarterback's hand.
Despite this certainly being of interest in league circles, to really grab the NFL's attention, the researchers knew they needed to turn this complicated statistical model into something digestible for fans and NFL front offices.
To accomplish that, they turned to West — a freelance motion designer — to translate their findings into an animated presentation that shows a visual model of a defensive back's possible movements once the ball is in the air.
Thompson said the project likely would've been impossible without West.
"We're statisticians. We can do the statistics, but a video? We wouldn't even know how to approach something like that," Miller said in a release, echoing Thompson's sentiment.
This year's team took home a $9,000 prize with the win, but perhaps more importantly, redemption, with a few members returning after not winning the year before.
Like a defensive back who gets beaten on a route, one of the best traits to have is a short memory. The next play could just as easily go your way — a mindset embodied by the team.
"Last year we worked really hard on the project," Nielson said in a release. "But a couple of things in and out of our control didn't go right, and we didn't win. The whole idea of coming back this year was, 'Hey, let's give it our best shot again.'"
