Sports analytics may be outmatched when it comes to artificial intelligence

Sports analytics may be outmatched when it comes to artificial intelligence

BOSTON (AP) — When it comes to artificial intelligence, the sports analytics crowd can be outnumbered.

The people who killed the victim and turned NBA games into a 3-point shooting contest aren’t quite sure what will happen when AI fully invades the sport — whether in the front office or on the court.

“I’ve been doing computer science for a long time. That’s the number one thing we don’t understand,” Philadelphia 76ers general manager Daryl Morey said Friday at the MIT Sloan Sports Analytics Conference.

“It’s mind-blowing,” Morey said. “We’ve actually created something, with 0s and 1s, where every step of the way we’ve done the creation, but we don’t understand the results.”

The MIT conference annually brings together thousands of numbers-crunching sports geeks who turn their data models around on hot topics like variety, gambling or reversing the slowing pace of baseball games. But this year’s gathering had a definite focus on AI, with panels and working papers on the potential for generative artificial intelligence to transform sports.

One talk looked at baseball strategy, another how to provide Olympic content for the more than 200 countries competing in four dozen different sports, and a research paper used AI to provide player tracking data from a soccer broadcast.

Morey, one of the conference founders, participated in a panel called “Winning with AI: The Future of AI in Sports.” The discussion touched on the potential for improvements in scheduling, player safety, advertising, ticket sales and broadcasts that turn the action on the field into a Disney cartoon.

Kevin Lopez, ESPN’s vice president of development and innovation, compared AI to the iPhone, which transformed everyday life by enabling anyone with some coding skills to create their own apps.

“I think of that when I think of generative AI,” Lopez said. “I don’t think anyone knows what it is yet. It’s fascinating to me and what the next thing will be.

“We exist at this point in history, in my humble opinion, where we’re seeing new incremental innovations in AI every day,” he said. “What will it be like for the freshman at MIT in two years.”

Make no mistake, though: AI is already here.

Broadcaster-turned-broadcaster Carlos Peña said artificial intelligence could be used to help a player eliminate his blind spots. (But players will balk, he said, unless it’s stripped of its “mathematics” and translated into simple guidelines like “look for the fastball up and in.”)

Anticipating complaints from scouts and others who say analytics can’t replace intuition, Peña said, “That’s not what we’re trying to do here. What we’re trying to do is improve intuition.

Christopher Jackson, head of digital data and analytics for the Olympics, said artificial intelligence could help create website content that caters to lower-profile sports fans from far-flung countries that don’t normally get mainstream media attention . One problem: Olympic planning is measured in decades, while major changes in AI happen every six months or so.

Amazon Web Services global head Julie Souza said the NFL is saving $2 million a year by using AI on its schedule, which has 1 quadrillion — that’s a one followed by 15 zeros — potential options that must account for holidays, shared stadiums and travel. AI is now analyzing which plays — and even which body positions — are most likely to cause injuries in a soccer game, she said.

“The rules are changing to make the game safer, to make the players more protected,” Souza said, adding that information can flow from football to the military and beyond.

“It’s not just the NFL that benefits from this,” she said. “We will not return. There’s no coming back from this. We’re just learning more and making the game safer. Which is great not only for the league but for us the fans to have more players on the field.”

Morey said the 76ers are using AI for productivity — speeding up routine tasks — but it’s not yet sharp enough to outperform the humans they have in trying to improve their predictive modeling. “We haven’t found a ton there, but that will change,” he said.

And they will keep trying.

“There’s a lot of scary stuff about it, but it kind of is. It happens,” Morey said. “There’s no way we’re going to do all the safety stuff. … In fact, there will be no way to control it. You really lean on that, frankly, to help your business, to help what you’re doing.

“And there can be a very scary thing you hit. But what is the alternative? You don’t hug him?” he said. “That doesn’t make sense.”


AP Sports:

Leave a Comment

Your email address will not be published. Required fields are marked *