Big Data Is Coming to the National Hockey League
This season, the league is debuting a puck and player tracking system that promises to unleash a tsunami of big data about player speed and execution
Big Data – In the last decade, data and analytics have turned baseball into a bonanza of home runs and strikeouts, basketball became a game won or lost behind the arc and even prompted football coaches to start going for it on fourth down.
Hockey, however, has barely evolved. “The NHL’s been behind the other sports with regard to the adoption of advanced metrics and analytics,” said Dave Lehanski, senior vice president of business development and global partnerships for the National Hockey League. “We don’t have a lot of the math that supports a lot of the subjective opinions that people have.”
Finally, however, a solution to this problem, pursued by the NHL for nearly 25 years, may finally be arriving later this season. And it’s inside the puck. As early as 1995, commissioner Gary Bettman explored implanting a tracking device into pucks to collect data for coaches and make it easier for television viewers to follow the puck while watching games on grainy standard-definition broadcasts. But progress came in fits and starts, and the NHL’s dreams outpaced technological innovation.
In 2013, the NHL renewed its focus on developing a trackable puck and finally, six years later, big data is coming to hockey. This season, the league will debut a puck and player tracking system developed by SMT, the sports technology company behind football broadcasts’ glowing yellow first-down line. The system promises to unleash a tsunami of data about player speed and execution—and change the way that coaches, broadcasters and fans interact with the game.
“The major upside for us is driving more engagement,” said Lehanski. “Right behind that is the ability to monetize this and generate incremental revenue for us and for our clubs.” The league hopes the enhanced data will make media rights more valuable and in turn generate more ticket and merchandise revenue. “We’re focusing on puck and player tracking, but what we’re talking about is much bigger than that,” said NHL chief technology officer Peter DelGiacco. “This data is a game changer.”
The biggest upside may come from a market that is not yet legal nationwide: sports betting. Bettman was once a staunch advocate of the sports-gambling ban in most states, but he is now embracing the market. The league put a franchise in Las Vegas in 2016 and has signed deals with MGM Resorts International, U.K. bookmaker William Hill and online daily fantasy platform FanDuel.
“Betting and what’s happened here…was not something we had on the table in 2013-14,” said Lehanski. “But it didn’t take long to say, ‘All right this data’s going to be hugely valuable.’ ” The benefits of having data on players and the pucks was obvious to the NHL. Building a trackable prototype puck was another story.
Quite hard, as it turns out. It took SMT nearly four years before it was ready to debut its prototype puck at the World Cup of Hockey in September 2016. According to Hall, those pucks functioned “flawlessly.” But the pucks were panned as ugly. Infrared sensors inside them required the pucks to have slightly raised nodules around the edges and a seam at the top to let light flow through the rubber. Shortly after the tournament wrapped, the NHL looked for a new firm to produce trackable pucks using radio frequency, which would not require external nodules or seams.
“I had Ph.D. scientists who are like, “Are you kidding me? The damn thing works!’ ” But that’s not the only thing that matters,” said Hall. “You start out with ‘Let’s just take a puck and saw it in half, let’s gouge out the interior of it and let’s see what happens when we stick some electronics in and then glue it back together,’ “said SMT founder and chief executive Gerard J. Hall. “How hard can it be?”
This article originally appeared on wsj.com To read the full article and see the images, click here.
Nastel Technologies uses machine learning to detect anomalies, behavior and sentiment, accelerate decisions, satisfy customers, innovate continuously. To answer business-centric questions and provide actionable guidance for decision-makers, Nastel’s AutoPilot® for Analytics fuses:
- Advanced predictive anomaly detection, Bayesian Classification and other machine learning algorithms
- Raw information handling and analytics speed
- End-to-end business transaction tracking that spans technologies, tiers, and organizations
- Intuitive, easy-to-use data visualizations and dashboards