Skip to content

PGA Tour is embracing artificial intelligence, and it could change how you watch golf

PGA golfers such as four-time major champion Rory McIlroy embrace the tens of thousands of data points - roughly 32,000 per event - that the tour’s ShotLink System has offered since 2001.
12554536_web1_glf-pga-ai-0690b67e-7d36-11e8-bb6b-c1cb691f1402
One of three ShotLink trucks the PGA Tour uses to collect data. Photo by: Chris Condon, PGA Tour

PGA golfers such as four-time major champion Rory McIlroy embrace the tens of thousands of data points - roughly 32,000 per event - that the tour’s ShotLink System has offered since 2001.

“I made the decision at the end of last year to really look at my stats,” McIlroy said after last week’s Travelers Championship. “I think they’ve become very important, and I think the strokes-gained stats, whether it’s tee to green or putting or around the green or whatever, I think that’s been one of the biggest changes for good that we’ve seen in golf, because it really just lets you see how your game stacks up against everyone else.”

Good news, Rory. For the first time Thursday at the Quicken Loans National at TPC Potomac at Avenel Farm, three fixed, high-resolution cameras, part of the tour’s upgraded ShotLink+ ball-tracking system, replaced the human-operated laser on every green of every hole, capturing the ball in motion as opposed to only the ball at rest.

“It’s the next phase of how we get the data without having to have human interaction on everything that happens,” said Matt Troka, senior vice president of product and partner management of CDW, a technology partner of the PGA Tour. “We went from a single point of data to thousands of points of data overnight.”

The amount of data collected by the PGA Tour is staggering. Alex Turnbull, director of the tour’s broadcasting production team, estimates there are 174 million shot attributes in the tour’s database, making it unwieldy for humans to make sense of them all. Instead, the PGA Tour is partnering with Microsoft and will use artificial intelligence to leverage 20 years of statistical data and 80,000-plus hours of video in its digital library.

Artificial intelligence, a term coined in 1950s by John McCarthy, a math professor at Dartmouth, simply means a computer will do things that require intelligence when done by humans. The NBA uses AI to make sense of its vast amount of shooting data, and the International Gymnastics Federation plans to introduce AI to help judge the Tokyo Olympics in 2020. The PGA Tour will use it, at first, to enhance its television broadcasts and digital storytelling.

“We want to enhance the entertainment value of our sport with ball-in-motion data,” said Steve Evans, the PGA Tour’s senior vice president of information systems. “The ShotLink broadcast team is focused on one broadcaster who is telling a specific set of stories. The broadcaster next door might be telling a completely different set of stories. And if you are writing for our digital content, it’s another set of stories. Instead of trying to scale that function with people, we are trying to automate it.”

The change might go unnoticed by fans watching a tournament, but the quality of the on-screen product should be much improved. Using an example supplied by the PGA Tour, Bryson DeChambeau missed the green on a par-5 at the Memorial in June, landing 57 feet from the hole. DeChambeau’s performance in these situations was instantaneously transmitted to the broadcast booth, providing the commentators with all the information they needed - such as that DeChambeau was leading the field with a scrambling rate of 80.0 percent - to provide color commentary. Even the most prepared broadcasters don’t always have the data they need at their fingertips; now it appears they won’t have to.

The tour will also use the AI platform to automate content creation, providing round recaps for every player in the field following every round of a tournament, and create more video highlights, allowing it to “easily put out 200 to 250 videos per week,” said Scott Gutterman, vice president of digital operations at the PGA Tour.

Video content for the PGA Tour is important. Unlike a basketball or football game, where everything is happening in front of you, golf tournaments have many moments happening simultaneously in different places, making it difficult to keep up with every player at every juncture of the event. Gutterman looked to the NFL as a possible solution.

“We are trying to figure out how to get video of every shot from every hole across the entire course so we can create something similar to the ‘NFL RedZone,’ which would allow you to go from green to green as players are getting ready to putt for birdie or win an event,” Gutterman said.

The tour plans to do much more with its data, with some of those advancements having a direct impact on sports betting and daily fantasy leagues.

Much like baseball’s analytics revolution in the 1980s and again in the “Moneyball” era, the PGA Tour is about to embark on a learning expedition. However, unlike Bill James’s Project Scoresheet, a plea to fans in 1984 to provide play-by-play accounts of every game because MLB would not, the tour will simply feed the machines and let them figure it out.

“This is all about taking this massive database of shot data and creating an artificial-intelligence system that finds the most relevant, most interesting stats that are contextual,” explained Mike Downey, an engineer at Microsoft. “So whatever is going on a golf tournament at that moment will know what is most relevant. The data will help add context so we can have a better understanding of how unique or special any given shot was.”

Perhaps we will learn, definitively, that driving distance isn’t as important as strokes gained off the tee, or that sand play at one event is significantly more important than at another. Maybe a player scrambles better at TPC Potomac than at Augusta National - critical information for sports bettors or daily fantasy players. First up: The PGA Tour will examine, in detail, how players perform on the green.

“We are going to create some new statistics around putting,” Evans said. “We are going to compute stats around putts that break from left to right, right to left, uphill and downhill. We are going to see what are the tendencies in general and then look at those tendencies by player.”

Perhaps that sounds like a small step for such a big database, but remember, baseball’s analytics revolution blossomed around one stat (on-base percentage), too. So there should be little doubt that golf is on the cusp of a significant statistical movement.

Neil Greenberg/The Washington Post