For the NHL, it was an all-hands-on-deck operation. It was early January in Las Vegas, and the league was testing its player tracking system in regular season games for the first time. The first game was between the Golden Knights and New York Rangers. Two nights later, came the second test – a game between the Golden Knights and the San Jose Sharks.
Advertisement
NHL commissioner Gary Bettman was there for this moment. So was deputy commissioner Bill Daly, and just about every person on the NHL’s senior executive group. The league extended invitations to all 31 teams to witness this breakthrough moment and large number accepted, although surprisingly not all. Many teams funneled the invitation from the business side to their analytics experts to try to get as much advance information on the coming data revolution as possible.
That’s where things got interesting.
There were vendors in Vegas to show some of the cool byproducts of this tracking technology. One team analyst put on goggles provided by a company that had been working with European soccer teams and suddenly he was on the ice. He could choose a player and see the game from their perspective, with a 360-degree view.
“Any moment where you’re making a decision, you can stop and look around and understand what’s going on. They recreate the game as a video game,” he said, still clearly impressed by the possibilities.
But it’s the data most were interested in, so when it came time for a private question-and-answer session with Martin Bachmayer, the CEO of jogmo.world, the technology company that is running the tracking system for the NHL, the talk got detailed.
“It was about technology infrastructure,” Bachmayer told The Athletic. “We walked them through the technical background, how the system works.”
These were some of the brightest minds in hockey front offices listening in – Washington’s Tim Barnes, Pittsburgh’s Sam Ventura, Toronto’s Darryl Metcalf, Tampa Bay’s Michael Peterson, Carolina’s Eric Tulsky, Minnesota’s Alexandra Mandrycky and Andrew Thomas, among others.
They were told that the system can track players at 200 times per second and the puck at 2,000 times per second. That each arena is being outfitted with 14-16 antennae in the rafters, to be supported by four cameras. Every player will have one sensor in their shoulder pads and 40 pucks at every game will be provided with sensors inside.
Advertisement
Then came the questions from analysts.
When will this data become available?
Will teams get access to the raw data?
Will there be any way to tie the puck and the players together so that it’s clear who has the puck?
What kind of manipulation will be done to the data before teams have access to it?
How much will be transmitted to teams in real time?
All valid questions.
Right now, they don’t all have answers. Even the timing of the tracking data implementation is very much up in the air. We know it’s happening next season. But when?
“We have a general timeline we’re working against. I don’t think the start of the season is likely,” said David Lehanski, the NHL’s senior vice president of business development. “We’re not going to compromise the integrity of the systems … there’s nothing more important than getting it right. I’d say at this point, midpoint of the season, to have every arena up and running would be a rational date or a general period to think about.”
And how will the data be presented to teams?
“We haven’t fully defined that just yet. We’re working on all that right now,” Lehanski said. “It’s about fully understanding exactly what we’re going to have, the format we’re going to get it in and the scale and scope of understanding what the teams want. … To hand everything to them out of the gate would be overwhelming.”
But if they ultimately want everything, according to Daly, they’ll get it.
“They have access to all the raw data,” Daly told The Athletic. “Whatever data we collect, they have access to. Whatever measurements it makes, they’ll have access to it.”
As will the NHLPA.
A big part of the process was a lengthy negotiation between the NHL and NHLPA to settle on what data could and couldn’t be collected, and how it would be used in player tracking. That negotiation has concluded.
Advertisement
The end result is pretty straight forward. The players agreed to have a chip in their jerseys but with the restriction that data can’t be used in contract negotiations or salary arbitration. No biometrics will be allowed. A start date is still to be agreed upon, and the NHLPA will have full access to everything.
A big motivation for both sides is to enhance the NHL’s game coverage on television, with the data providing all kinds of options for new graphics, from players identifications and speed to the exact distance between players on the ice shown in graphic form. Gambling is another big motivator with player tracking allowing all kinds of new proposition bets – like total distance skated by a player during a game or getting odds on exactly where on the ice a player might score the next goal.
But the biggest impact may ultimately come in how individual teams use this data. Many franchises are already formulating plans to capitalize on the mountain of data that’s about to arrive in their front offices.
It’s believed that the Toronto Maple Leafs, New Jersey Devils, Tampa Bay Lightning, Carolina Hurricanes and New York Rangers are among the franchises either adding to their analytics staffs or considering it. That’s likely just the tip of the iceberg.
“I think the league tracking data is a leading reason for me to use in support of asking for help I was already looking for,” said one team analyst.
A recent polling of general managers on how they plan to handle the coming firehose of data found a variety of responses:
“I want to see what it is first,” said Blackhawks GM Stan Bowman. “I’m not anticipating hiring a bunch of people. I think you’ve got to figure it out. It’ll be a process of learning – ‘How is this going to help us? What am I going to do with it?’ Until it comes out, I think for me, it’s premature to be jumping in.”
Advertisement
“I think it’s going to be, ‘Let’s see what we get and let’s figure it out as we go,’” said Capitals GM Brian MacLellan. “I don’t know that we know. We sent our guys to the meeting on the data presentation. I don’t know that they have any concrete (ideas) on how we’re going to use it.”
Said Maple Leafs GM Kyle Dubas: “Once we get a sense of the exact methodology in which the data is going to be delivered, then we’re either going to…hire new people or maybe divert some of our resources we’re spending on our current things we’re doing into deciphering that data into usable knowledge.”
“The best way to prepare for a mountain of data is to already have had a mountain of data,” said Coyotes GM John Chayka. “We’ve been working with large data sets for a number of years. … I don’t know how much our approach or infrastructure and analysis is going to change. As more teams have better access to more data, the market inefficiencies shift. You want to stay ahead of that curve.”
“We’re trying to incorporate many people into our group already,” said Sabres GM Jason Botterill. “To me, it’s making sure you have the people at the top that can decipher the information. It’s going to be more of a decision about how much manpower you need for the information.”
“We don’t necessarily have a billboard up who is working for us in analytics. We have some people behind it… We’re always looking for new ways,” said Rangers GM Jeff Gorton. “One of the luxuries of New York is we have the ability to get more people to add to those departments, so yeah, we’re looking at that.”
It goes beyond adding staff. Some general managers are currently looking to other sports for insight. Lightning GM Julien BriseBois talked with multiple NBA teams about how they’ve best utilized player tracking. His biggest takeaway? It may take years for NHL teams to capitalize on what’s coming next season.
“You need to compile sufficient data over a sufficient period of time in order to have something that starts to mean something,” BriseBois said. “(The NBA) has been collecting data and analyzing data for many years and it really took years before they were able to start actually make decisions based on this data.”
Advertisement
Dubas also leaned on the NBA to get a head start on the best utilization of the tracking data.
“We have a major advantage,” Dubas said. “We have the Raptors down the hall. Their group and management have been at the forefront of this type of stuff. It’s been a major benefit for us.”
Dubas’ conclusion is that the initial focus isn’t on trying to implement a plan to use this data as quick as possible. The focus now has to be on developing a process for how the franchise will use it.
“Darryl Metcalf heads all that up for us, having him start to get in tune with what exactly is going to be made available so that we can begin our preparations for, not how we can directly use it but what the information is and develop a process for how we can use it,” Dubas said.
And while NHL teams may have an in with their NBA counterparts, the best place to look for hints at hockey’s future is over to Europe where player tracking is revolutionizing soccer.
Paul Power is an artificial intelligence scientist for the sports intelligence company STATS. Based in Leeds, England, his focus is primarily on soccer but you can hear the excitement in his voice, even over a spotty Skype connection, about the possibilities player tracking brings to hockey.
He broke the potential impact of player tracking data in hockey into three key components:
1. Athlete monitoring: Power suggests that gathering data like players’ skating speed over the course of several games will help build a better understanding of the physical load a player can exert in a game. It will help teams make their distribution of minutes more efficient. “If you can get your best players out there more than you thought, that’s a huge advantage,” Power said. He shared an example from rugby, where a team discovered that a player who started the game after the first 10 minutes had elapsed could play longer because the first 10 minutes are so intense. “They could maximize his performance,” he said.
Advertisement
2. A better understanding of context: “A huge issue with the current statistics in hockey is it’s very reductionist,” he said. He used passing data as an example. There may be data now as to whether a player completed a pass but there isn’t a wealth of context around it. “Was the guy under pressure? Did you have an overload on a certain part of the ice?” Power explained. “Being able to identify these situations, it allows you to measure how a player copes in these situations and test scenarios.” The next step is to then take the tracking data and simulate how defenders will respond in order to draw up the most effective strategy in real time. “In basketball, which is similar to hockey, imagine the last 20 seconds, you’re down by one and you have to come up with your play,” Power said. “You can draw a play that you want and because you can use all the tracking data, we can learn what you’re drawing and simulate what’s going to happen with the defense and what’s the most likely outcome. They’ll draw something on the fly, imagine being able to test that scenario quickly.” It sounds like something way off in the future, but Power said it’s already being done by the most progressive teams in soccer.
3. Roster construction: Once you’re able to use the tracking data to build models, you can better profile players who fit the needs of the roster and the specific tactics of your coach. “You can better profile players if you can look at movement patterns that your coach implements,” Power said. “Particularly if you have the league-wide data, you can pick out the players who best fit into your style. And then the opposite – who doesn’t fit?”
Soccer is certainly ahead of hockey in using this data and Power has observed a bit of a tipping point over the past 12 to 18 months where teams are seeing the impact of the data and actually believe what can be done. The sport has moved beyond the questioning phase.
Hockey, as the NHL builds out its player tracking platform, is very much entering the questioning phase. And therein lies the potential advantage for teams that capitalize.
Power joked that his first approach, if he were in charge of an NHL team, would be to tell everyone publicly that player tracking can’t help hockey and that hockey is its own unique sport where nobody will benefit from the data. Then he’d work internally to design a system in-house to best capitalize on the data and put a team and the technology in place to do it.
He’s confident the results will come. He’s seen it in other sports. The biggest question now is simply the timeline.
“That’s like asking how long a piece of string is,” he said. “It completely depends on the ethos of the GM, owners and coaches. … You could get instant results in the season. Some teams it’ll never happen. It’s not because they haven’t got stuff in place. It’s because they don’t have the right ethos throughout the organization.”
(Top photo of testing the chip tracking in a Golden Knights-Sharks game: Jesse Granger/The Athletic)