Engineering the perfect NHL team: U of T Engineering researchers create draft optimizer for new Las Vegas expansion

From left: Ben Potter (IndE MASc candidate), Michael Shin (EngSci Year 4), Rafid Mahmood (IndE PhD candidate), Yusuf Shalaby (IndE 1T7), Professor Tim Chan (MIE) and Albert Loa (EngSci Year 3) used their expertise in operations research to create a tool that drafts the optimal roster for the NHL’s new expansion team, the Las Vegas Golden Knights. (Credit: Marit Mitchell)

Hockey fans around the world are waiting anxiously to find out who will be drafted to the NHL’s new expansion team, the Las Vegas Golden Knights.

Industrial Engineering Professor Timothy Chan and his team of students already have an idea of who may have made the cut — though no one will know for sure until the Golden Knights’ general manager George McPhee makes the draft announcement on June 21.

Chan’s research group has developed and launched the web-based modelling tool that takes a deep drive into the draft data to predict what the 2017-18 Golden Knights roster may look like.

“We’re all big sports fans, and we were speculating about the expansion draft,” said Professor Chan, who worked with a team of five U of T Engineering students, including undergraduates and graduate students, over the course of a month to develop the site in time for the draft. “Knowing that the announcement was coming up, we thought this website would be a great tool to show operations research in action.”

Using the optimization model the group designed, the site determines who the Golden Knights should pick from the NHL’s 30 teams to maximize the “value” of their roster, taking into consideration the draft rules. The optimizer selects:

  • One player from each existing club for a total of 30 players
  • A minimum of 14 forwards, nine defensemen and three goaltenders
  • A minimum of 20 players who are under contract for the 2017-18 season
  • Players with an aggregate Expansion Draft value that is between 60-100 per cent of the prior season’s upper limit for the salary cap

It also allows hockey fans to fine-tune the results to their liking and sports expertise, choosing which players to “protect” or which to “expose” to the draft, and adjusting the metrics for what they think would be most valuable for the team, such as optimizing based on a player’s on-ice performance, or even by their EA Sports NHL 17 player rating. Fans can also get a sense of which players they could lose from their favourite team.

“This is bringing operations research out to the mainstream audience. Classically, OR is used very internally — a general audience may understand the concept of optimization, but they can’t explain what it is,” said Rafid Mahmood (IndE PhD Candidate). “This NHL optimizer brings it to the forefront, and shows why OR is so valuable.”

Ben Potter (IndE MASc candidate) knew the optimization model they created was doing its job when he noticed a name that kept popping up in the media and in their optimizer: The Chicago Blackhawks’ Trevor van Riemsdyk. “I don’t know a lot about the NHL but one of the recurring results was Trevor van Riemsdyk, and someone pointed out that there was speculation in the news that the Golden Knights were going to select him as part of a larger deal with Chicago.”

The website also clearly highlights some difficult situations some teams are facing in order to protect their star players. For example, the model indicates that the Pittsburgh Penguins’ starting goalie, Matt Murray, is slated to be exposed and chosen by Vegas, since their back-up goalie, Marc-Andre Fleury, has a no-trade clause in his contract.

“If the draft were held today, that’s very likely what would happen,” said Chan. “However, most pundits believe that Pittsburgh will somehow find a way to keep Murray via trades or a side deal with Vegas.”

After McPhee makes the big draft announcement, and the roster of the 31st NHL team is known, Professor Chan’s group plans to have a post-mortem to see how well their optimizer did in predicting the team. After that, they hope to find other applications for their model.

“The foundation that this was built on can be applied to a lot of other problems that require on-demand optimization. It could be useful for anything from scheduling to fantasy sports,” said Chan. “Of course, in the short term, if the Golden Knights want to use our team for some consulting, we’d be OK with that too.”

This article originally appeared in U of T Engineering News. Article published by Liz Do.