clock menu more-arrow no yes mobile

Filed under:

Virginia engineering students help Cavalier football program develop mathematical edge

Data analytics take center stage for Mendenhall, coaching staff

NCAA Football: Boston College at Virginia Geoff Burke-USA TODAY Sports

If you follow Virginia sports here on Streaking the Lawn, you know we love using new-age stats to help tell the stories of the Cavaliers.

Tim Mulholland did it to explain to to Triangle troglodyte Caulton Tudor why Mike Scott should have been a unanimous first-team All-ACC selection in 2012. KenPom’s pace-adjusted numbers are indispensable when evaluating a basketball program that has fewer possessions per game than any other NCAA team, year after year.

Fancy numbers are making their way into our football coverage, too. They can tell us what an opponent’s weak spots might be in a game preview, or how a newly hired coach can help a particular unit improve. Bill Connelly’s Football Study Hall should be a go-to resource for any college football fan.

It turns out the Virginia Cavaliers football coaches are using advanced analytics, as well. But they aren’t using them to tell a story. They’re using the numbers to write a whole new chapter themselves.

Whitelaw Reid has a great story from UVAToday on how current students are helping the coaching staff build models for everything from recruiting, to practice, to in-game decision-making.

On the recruiting front, the models help the coaches identify under-appreciated talent, determine a recruit’s mentality through their social media profiles, and efficiently expend resources on recruits most likely to value what UVA offers.

For example, here’s how the model works for determining whether a prospect would be attracted to UVA:

The recruiting team spent two semesters adding features to an analytics model, which the students the year before created, that predicts the likelihood of recruits choosing UVA. The idea is to give Cavalier coaches an idea of which players they have a legitimate chance of signing so that they don’t waste time and resources elsewhere.

Pulling data from recruiting websites and the U.S. Census Bureau, the model draws from roughly 30 criteria, including how far UVA is from a recruit’s hometown, the weather of a recruit’s hometown compared to Charlottesville, whether the player has made an official visit and the success of the programs he is considering.

The model then spits out percentages for all the players being recruited that are incorporated into UVA’s recruiting database, “War Room.” The higher the percentage, the more likely a recruit is to select UVA.

That’s wild. (War Room, by the way, is software that Mendenhall developed at BYU to help with both recruiting and roster management. This isn’t his first dip into these waters.)

Matt Edwards—grandson of BYU legend and passing-game trailblazer LaVell Edwards—has been the numbers guru on the performance and gameday side since joining the UVA staff in 2017. The student-developed models help him help the play-callers adjust on the fly.

Just how cutting-edge are these student projects?

Last February, Edwards couldn’t help but smile when he attended the annual MIT Sloan Sports Analytics Conference in Boston, where some of the best and brightest minds presented projects they were working on.

“It was almost the exact work that we were doing on our own,” he said.

Next we’ve got to figure out a name for this approach. “Moneyball” is already taken, but “MendenBall” has a nice ring to it.