Bloomberg
January 6, 2023
When the National Football League began seriously studying concussions six years ago, its focus initially was head trauma. Radio-frequency identification (RFID) tags were placed in helmets, shoulder pads and even mouthpieces to gather metrics about each player’s speed, distance, orientation and the direction his head moved. (The tags are placed on every player for all games and practices.)
This data is now being used to study more than just concussions. Last year the league created the Digital Athlete, an initiative that uses computer simulation to reconstruct scenarios in which injuries of all types occur. “It allows us to understand: Why did this player get injured? And then identify things we could do to change that outcome,” says Sam Huddleston, principal data scientist at Biocore LLC, the NFL’s engineering partner.
These moves come amid intense scrutiny about how the NFL can make an inherently violent sport more safe. On Jan. 2 the Buffalo Bills’ Damar Hamlin suffered cardiac arrest on the field after being hit in the chest. In another nationally televised game earlier in the season, Miami Dolphins quarterback Tua Tagovailoa’s hands showed signs of a neurological injury after he hit his head on the turf.
But there is some evidence the Digital Athlete initiative is working. One of Biocore’s findings was that load management in preseason training has been completely backward. For decades, teams began preseason practices aggressively and then cut back on the amount of physical contact at the end. But by starting out hard, players often got injured early. “Slowly ramping the load will pay off for you in the end,” Huddleston says.
The NFL mandated this ramping-up effect last year, limiting how many minutes players could practice in their first four days back. The results, the league reports, are “significant,” including “a 26% year-over-year decrease in lower extremity injuries during the first two weeks.”
More data-based decision-making is coming. In December the league announced the Contact Detection Challenge to “predict player injuries through machine learning and computer vision.” The winner, to be announced in March, will receive $100,000.
Analytics will also change how sports are broadcast. Toronto-based Eon Media Corp. has developed a proprietary algorithm that allows advertisers to measure, to the second, how much screen time their logos receive on specific players’ uniforms. “We can tell a sponsor that the camera operator needs to position in a certain region to get the most exposure,” says Chief Executive Officer Ashish Agrawal.
A study of the 2022 US Open golf tournament, for instance, found that a logo got twice as much exposure on a hat as it did anywhere else on the body. Oddly, sponsors on a golfer’s left sleeve consistently got more exposure than on the right sleeve, regardless of whether the player was left- or right-handed. Agrawal says his company can also quantify the demographics of an arena within seconds—valuable information for team owners and television partners to “realize the overall value proposition.”
Eon was among the first companies to receive funding from the Comcast SportsTech Accelerator, which invests in and fast-tracks sports-related startups. Comcast Corp.’s Jenna Kurath, who heads the program, uses the example of the Philadelphia Flyers hockey team, which Comcast owns. “We’ve got tons of logos in the Wells Fargo Center,” where they play, she says. “But are we monetizing that in the best way? It’s really valuable data that we just haven’t had before.”