Please take a moment to ponder the horse racing equivalent of the details offered in today’s edition of #FreeDataFriday.  

Entries are open for the National Football League’s 2020 Big Data Bowl. No, it’s not quite the Super Bowl, but the league and its franchises are hoping a focus on analytics can help change the sport.

As described by the NFL, the Big Data Bowl is an “annual analytics contest [that] explores statistical innovations in football – how the game is played and coached.” They report that 11 participants from the 2019 Big Data Bowl have since been hired by NFL teams or affiliate vendors.

The 2019 edition was the inaugural version, with finalists presenting their findings to league officials and representatives of the 32 teams at the NFL Combine earlier this year. Teams of analysts competed in two divisions – those at the collegiate level and open entries. A team from British Columbia-based Simon Fraser University landed the top collegiate prize.

“The group modeled play success rate and expected points under various passing route combinations. Using a technique called model-based clustering, the group found several complementary pass route patterns that could consistently yield positive outcomes, even when accounting for defensive formation and behavior.”

Nathan Sterken won the open entry division. According to the NFL’s report on the event, “Sterken treated receiver routes as an image recognition problem, using a neural network to categorize each route. Once grouped, these patterns were compared to win probability added (the change in the offensive team’s chance of winning the game before and after the play).”

Project synopses from other university finalists in the Big Data Bowl included the following:

- Duke University: A trajectory planning algorithm for quantifying space ownership in professional football. [Use] metrics like player speed, direction and acceleration to chart the space occupied by the 22 players on the field. One example highlighted a 64-yard touchdown pass from Derek Carr to Johnny Holton to show how Holton’s speed and direction indicated that he was moving towards an open space well before he looked open on the field.

- Carnegie Mellon University: DIRECT: A two-level system for defensive interference rooted in repeatability, enforceability, clarity, and transparency. [Merging] statistical modeling techniques with potential changes in penalty calls and receiver catch probability to consider new standards for defensive pass interference and defensive holding.

- University of Pennsylvania: Using auto-encoded receiver routes to optimize yardage: The group presented three unique ways to represent pass route data, including time series and shape-based clustering. Merging in-play and game-specific traits, the group suggested that hitch routes are generally an underused strategy for increasing efficiency.

The 2020 edition of the Big Data Bowl remains open.

To learn more about the Big Data Bowl, click HERE.​​​​​​