Sports analytics can be overwhelming when it comes to AI.

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

BOSTON – When it comes to artificial intelligence, the sports analytics crowd can be overwhelming.

Those who killed the sacrifice bunt and turned NBA games into 3-point shooting contests aren’t sure when AI will fully invade sports — even in the front office. Either in the field.

“I’ve been in computer science a long time. This is the number one thing we don’t understand,” Philadelphia 76ers team president Daryl Morey said Friday at the MIT Sloan Sports Analytics Conference.

“It’s heartbreaking,” Morey said. “We’ve actually created something now with 0s and 1s, where every step we’ve created, we don’t understand the results.”

The MIT conference brings together thousands of underdog sports pioneers each year, who transform their data models into hot topics such as diversity, gambling or the slow pace of baseball games. But this year’s gathering had a decidedly AI focus, with panels and working papers on the potential for creative artificial intelligence to transform sports.

One talk was on baseball strategy, another on how to provide Olympic content for more than 200 countries participating in four dozen sports, and a research paper on providing player tracking data from soccer broadcasts. AI was used.

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

Kevin Lopes, ESPN’s vice president of development and innovation, compared AI to the iPhone, which changed everyday life by allowing anyone with some coding skills to come up with their own applications.

“That’s what I think of when I think of creative AI,” Lopes said. “I don’t think anyone knows what that is yet. It’s exciting to me, and what’s going to happen next.

“We’re at this moment in history, in my humble opinion, that every day we’re seeing new incremental innovations in AI,” he said. “This is what’s going to happen to a freshman at MIT in two years.”

Make no mistake, though: AI is already here.

Ballplayer-turned-broadcaster Carlos Pena said AI could be used to help eliminate a batsman’s blind spots. (But players will resist, he said, until the “math” of it is stripped away and translated into simple guidance such as “Find the fastball up and in.”)

Anticipating complaints from scouts and others who say analytics can’t replace intuition, Pena said: “That’s not what we’re trying to do here. What we’re trying to do is They are to enhance intuition.”

Christopher Jackson, head of digital data and analytics at the Olympics, said AI could help tailor website content to satisfy low-profile sports fans from far-flung countries that are typically overlooked by mainstream media. Do not attract attention. One problem: Olympic planning is measured in decades, while major changes in AI come every six months or so.

Julie Souza, global head of Amazon Web Services, said the NFL is saving $2 million a year by running AI on its schedule, which has 1 quadrillion — followed by 15 zeros — possible options, including holidays. , joint stadium and travel should be accounted for. AI is already determining which plays — and even which body poses — are most likely to cause injuries in a soccer game, he said.

“The rules are changing to make the game safer, to make the players safer,” Souza said, adding that the information could go from football to the military and other fields.

“It’s not just the NFL that’s benefiting from this,” he said. “We’re not going back. There’s no going back. We’re just learning more and making the game safer, which is not only great for the league, but great for our fans and our players. to be brought into the field more.”

Morey said the 76ers use AI for productivity — speeding up routine tasks — but it’s not yet fast enough to surpass humans as they try to improve their predictive modeling. are doing “We haven’t found a ton there, but that will change,” he said.

And they will keep trying.

“There’s a lot of scary things with it, but it’s kind of there. It’s happening,” Morey said. “There’s not going to be any way to do all the safety stuff. … There’s really no way to control it. You really just lean into it, honestly, to help your business, what you’re doing. To help with this.

“And there could be a very terrible thing that you killed. But what’s the alternative? Not embracing it?” They said. “It creates no awareness or discernment.”

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

Leave a Comment