AI-driven coaching coming to NHL

[Reggie Dunlop]

NHL Ice hockey team, the San Jose Sharks, is working with Cambridge Consultants, part of Capgemini, and sports advisory firm Sportsology to examine how artificial intelligence could support coaching decisions.
The collaboration aims to assess whether AI can offer fresh perspectives by analysing in-game data differently from traditional methods. The team hopes the technology can help identify patterns in player movement and game dynamics that may not be evident to human analysts.

https://techinformed.com/san-jose-sh...iven-coaching/

[ComixZone]

Because they heard AI could finally compute a positive Corsi for percentage and optimize their xG against in real-time, something their human coaches apparently couldn't algorithm their way out of!

This joke provided by Gemini 2.5 Flash.

[traptor]

hopefully we see some wacky strategy changes out of it.

[Itse]

AFAIK AI generally isn't good in figuring out new things to do with data, but it can be very useful in keeping track of large amounts of data that's constantly incoming.

(Pretty sure calling it "AI" is probably BS according to experts, but sports always love buzzwords anyway.)

[bluejays]

Originally Posted by Itse

AFAIK AI generally isn't good in figuring out new things to do with data, but it can be very useful in keeping track of large amounts of data that's constantly incoming.

(Pretty sure calling it "AI" is probably BS according to experts, but sports always love buzzwords anyway.)

Consultants are mostly bs IMO. Someone was sold on some fancy presentation, a great pitch guy, and now will charge the organization and arm and a leg to implement. Then they’ll go with another consultant who will blame Capgemini, and they’ll put in their own system. Rinse and repeat. Consultants…

[CalgaryFan1988]

It will never be used in Edmonton, having Intelligence.

[Rick M.]

I can hardly wait for Robo-Darryl.

[traptor]

Originally Posted by Itse

AFAIK AI generally isn't good in figuring out new things to do with data, but it can be very useful in keeping track of large amounts of data that's constantly incoming.

(Pretty sure calling it "AI" is probably BS according to experts, but sports always love buzzwords anyway.)

I don't think that's true necessarily.

AlphaGo showed that AI can figure out new things, but typically in very specific areas. It learned new strategies in the game of Go by playing millions of games against itself.

So while some AI mainly helps manage lots of data, others like AlphaGo can discover new ideas within a set of clear rules.

And yes, “AI” is often overhyped, but there are different types, from simple data tools to focused but strategic systems like AlphaGo. It depends on how the AI is built and trained.

[Reggie Dunlop]

Robot Referees are next.

[Shazam]

Can't wait for it to hallucinate a seventh player.

[Wolven]

I would rather see AI being implemented to address offsides. That would be an easy win for the NHL to eliminate those goal call-backs from an offside 2 minutes ago.

[dissentowner]

Originally Posted by Reggie Dunlop

Robot Referees are next.

I wish. The current ones are trash.

[manwiches]

It was only a matter of time.

I've embraced AI fully in my personal and work life, and it has made my life infinitely easier.

Regarding the personal side, I coach my son's hockey and soccer teams. I used AI all last season to help me build out practice plans. I analyze how the practices go, and then next practice, I tell AI what worked and what didn't, and what i want it to focus on. I have a built in resource library it pulls from from various sources online and what I have downloaded and uploaded into it's resource library that is calls on and references.

Quite honestly, it's taken so much of the grunt work that I normally would do manually.

Everybody gets all butt hurt and offended about AI because they think it's taking away work, but they don't realize that it gets you to the 80% of the way, but then one needs to apply the human element and bring it to the finish line the rest of the 20%. It's only as smart as the person analyzing it.

[Rick M.]

Originally Posted by Reggie Dunlop

Robot Referees are next.

My guess they’d blow a fuse when trying to understand the concept of game management.

[Shazam]

Treliving or an AI GM?

[icarus]

Originally Posted by Wolven

I would rather see AI being implemented to address offsides. That would be an easy win for the NHL to eliminate those goal call-backs from an offside 2 minutes ago.

How about goal line technology? Will we ever be able to figure that out?

[MrButtons]

Originally Posted by traptor

I don't think that's true necessarily.

AlphaGo showed that AI can figure out new things, but typically in very specific areas. It learned new strategies in the game of Go by playing millions of games against itself.

So while some AI mainly helps manage lots of data, others like AlphaGo can discover new ideas within a set of clear rules.

And yes, “AI” is often overhyped, but there are different types, from simple data tools to focused but strategic systems like AlphaGo. It depends on how the AI is built and trained.

Not to derail too much I read Nexus and Yuval Harari spoke about how AI is great at a few things but not at others and actually used the go example.

He calls it Known Knowns - things we know we know, we understand the problem and the solution or how to build it. Examples are playing Go, optimizing delivery routes etc.

it'll be interesting how something like this plays out for hockey, because it partially falls into what Harari calls Known Unknowns, or things we know we dont know. His example is consciousness, emotions and general intelligence. We know they exist but no clue how to replicate it.

I bring that up just because we hear the term Hockey IQ so much. But do we really know how to define that or make a goal set? to be able to have AI help we need to work to understand what exactly it means and how to track it. But back to the go example, maybe we need the supercomputer to connect data points that we know are there, but our brains cant connect themseveles (similar to new techniques to win go). Either way, its super interesting imo.

[Wolven]

Originally Posted by icarus

How about goal line technology? Will we ever be able to figure that out?

I think the answer is yes. However, offsides would be easier to implement and introducing this amount of technology to a professional sport should start with the easy wins.

When you think about what Amazon is trying to do in the Kraken arena with the automated food and beverage shops trying to track dozens of people and hundreds of items to make a seamless shopping experience... tracking ~16 bodies on the ice (in distinct uniforms) and 1 object to determine if the play is onside/offside as the object crosses a big blue line should be incredibly simple.

If they could get rid of that one situation where goals are being called back because of a missed offside call then that is an improvement to the fan experience. We would all rather have offsides be called down immediately and accurately than go through the excitement of having your team score only to have the goal nullified.

[Shazam]

You don't need AI to determine offsides. It's not a hugely complicated problem.

[GreenLantern2814]

Originally Posted by Shazam

You don't need AI to determine offsides. It's not a hugely complicated problem.

That Hawkeye #### that tennis uses would solve these offsides reviews overnight.