Tracking Evolving Fandom at the NHL with Posit & Snowflake
Summary
Jamie Shive, Director of Data Science at the National Hockey League, recently joined our weekly Data Science Hangout, and this spotlight is a recap of that conversation. Jamie calls her team's work "Fanalytics." Using Posit and Snowflake, her team works to understand what brings fans to games and keeps them spending. The data shows fandom evolving from team loyalty toward player loyalty, and this year revealed something unexpected: a hockey-adjacent fan fiction wave that sent engagement numbers "off the charts."
About:
The National Hockey League is a professional ice hockey league in North America composed of 32 teams, 25 in the United States and 7 in Canada.
Industry:
Sports
Technology used:
Posit Workbench
Data Cloud Partner Integration:
Snowflake
Photo by Alex Korolkoff on Unsplash
What fan analytics actually means at the NHL
Jamie Shive is the NHL's Director of Data Science, and the mandate she describes is deceptively simple. “What is driving you to go to a game? What is driving you to make a purchase? When you go to the game, what do you do there? Do you buy food? Do you buy merch? Do you get to the game twenty minutes late because there is traffic? And how can we help make sure that you have the smoothest experience possible?” That's predictive and descriptive modeling, run against a fan base in the tens of millions, for a league that makes almost all of its money by getting people through the gate.
Shive leads a team of three, and they've taken to calling the work “Fanalytics.” “I have been told that it is corny and cheesy to call it Fanalytics.” she said. “I am corny and cheesy. I'm going to call it Fanalytics anyway.”
Fan analytics at the NHL used to run across a patchwork of disconnected tools. The process looked like downloading CSVs locally, using a virtual machine to tap into a hosted R environment, running the R code, exporting the outputs back out as CSVs, then uploading those into a Business Intelligence tool for insights. Between the manual nature of the process and data going stale before it ever reached stakeholders, the whole thing was clunky. Now, with Posit and Snowflake, Shive says, "we have a streamlined process for analyzing and modeling these spikes and their impacts as the data becomes available."
The NHL's fan analytics team runs its everyday modeling inside Posit Workbench Advanced, deployed as a Snowflake Native App, a single governed workspace where R and Python run directly against the league's fan data inside Snowflake.
Evolving fandom
From Team Fans to Player Fans
Shive grew up the way most hockey fans do. “I didn't really have an option to be anything but the fan [of the team] that my parents and siblings and friends were fans of,” she said. “I'm a fan of that team. Doesn't matter who's on it. Doesn't matter who's leading it. Doesn't matter how they do.” That's the traditional model: you inherit a team, and the roster is almost beside the point.
Her team at the NHL is now watching the early edges of something different. “We're seeing the early signs of evolution from fan of team to fan of players,” she said. “Players move teams. So the change then is, on a club by club basis, this is what your fans are doing, but I'm thinking, we're years away from this, what it would be like to change the perspective of, fans of this player behave in this way.”
One signal is small but telling: fans occasionally go into their NHL.com profile and change their favorite team, almost always because a favorite player got traded. It doesn't happen often, changing your team on record is a real decision, not a passive one, but when it does, it shows up clearly in the data. Layer in what the team sees on social media, where casual fans follow individual players far more closely than they follow a club, and a picture starts to form of fandom organized around people instead of logos. It skews younger, too. “This is important to know because those are the ones who are going to be filling the building soon,” Shive said.
Hockey
is for
everyone
The Week Everything Went Off the Charts
Then, this year, something arrived that had nothing to do with any of that strategy. A piece of hockey-adjacent fan fiction, the kind of thing that builds a following entirely through word of mouth online. This year it reached a wider audience through a new run of episodes, and almost overnight, the NHL's own data lit up.
“All of a sudden, we noticed that the numbers were really different on demographic slices,” Shive said. “Who was coming to the games, who was interacting in a variety of different ways, who was new to the warehouse that we'd never seen before, and when did they enter, and was it after episode four or episode six or seven? It's all of them. We absolutely saw it.” Follower counts and video views climbed past anything the team's social analytics lead had tracked before. “Everything was literally off the charts,” she said. “Everything was off the charts.”
Shive is careful to draw a clear line around what the league can and can't take credit for. “We had nothing to do with it, and that's okay,” she said. “It's really lovely that that helped to show folks that hockey exists. Hockey is for everyone. Please come. Please enjoy it. You're welcome here.”
It's not the first time a piece of pop culture has done this to a sport. Shive points to the same pattern in the so-called Taylor Swift effect on NFL viewership, and in what Ted Lasso did for interest in club soccer among viewers who'd never followed it before.
Growing the female fan base had already been a season-long league initiative, with baselines and tracking in place well before any of the above started. The team is now a full season into tracking whether the spike in attention turns into fans who stick around. “This happened in the off season. I've been tracking for a full season, and now I'm excited to see what comes out of that,” she said. “TBD.”
What Comes Next
Shive's read on where this is headed ties back to the same values that shape the rest of her team's work. “Everything that I do in the fan space is making the game as accessible as possible to all of the fans who are here, and making sure that they can be themselves so that they can enjoy the game as much as possible,” she said. Hockey's fan base is getting more diverse, more player-driven, and less predictable by the season. The infrastructure now exists to actually keep up with it.
Learn from other Snowflake x Posit customers
Brilliant Earth
DairyNZ
