Generative AI Transforms US Open Experience
Key Points
- The episode explores how “openness” in AI is reshaping industries, with a focus on generative AI’s role at the US Open tennis tournament.
- Brian Ryerson, Senior Director of Digital Strategy for the USTA, explains the organization’s mission to promote tennis as a health‑and‑wellness activity and highlights the US Open as its flagship global showcase.
- IBM’s three‑decade partnership with the USTA now leverages the IBM Granite Family large language model, built on the watsonx platform, to automatically generate match insights, spoken commentary, and post‑match summaries for the tournament’s app and website.
- These AI‑driven content tools enable the USTA’s editorial team to cover significantly more matches, delivering richer, real‑time experiences to the millions of fans worldwide.
- The season’s broader goal is to reach over a million fans for the upcoming US Open, illustrating how open, generative AI can expand audience engagement at scale.
Sections
- Generative AI Enhances US Open - Malcolm Gladwell introduces US Tennis Association’s Brian Ryerson to discuss how IBM’s open, generative‑AI solutions deliver scalable match insights, spoken commentary, and post‑match summaries for millions of US Open fans.
- Digital Director’s Journey at US Open - Brian recounts his path from a marketing and technology graduate and lacrosse player to becoming the US Open’s digital director, overseeing consumer engagement for a growing food‑and‑wine tennis festival.
- Crafting Real‑Time Sports Narratives - The speakers discuss how storytelling drives fan engagement at the US Open, balancing planned narratives with unpredictable match outcomes to appeal to diverse audiences.
- IBM‑USTA Digital Partnership Highlights - The speaker describes a 30‑year IBM consulting partnership that equips the USTA with digital tools and AI‑driven video highlights, turning lengthy tennis matches into three‑minute clips delivered to fans almost instantly.
- US Open App: Fan Guide Overview - Brian explains that the US Open app serves as an on‑site companion for the millions of attendees, offering schedules, live scores, match previews, post‑match summaries, and integrated SlamTracker features to enhance the tournament experience.
- AI-Powered Tennis Shot Visualization - Brian explains how AI can instantly render every ball’s trajectory with layered statistics, turning standard broadcasts into an interactive, data‑rich experience for fans and analysts alike.
- AI-Powered Tennis Match Reporting - The speakers explain how Watsonx generative AI transforms tennis’s rich structured and unstructured data into full‑scale, automated match stories, enabling comprehensive coverage and new fan outreach worldwide.
- Ensuring Data Accuracy & Scaling Real‑Time Summaries - The speakers discuss validating data sources using watsonx tools and continuous model retraining, then leveraging IBM Granite models to handle real‑time summary generation across 22 simultaneous courts.
- Ensuring AI Data Quality & Risk Management - Brian outlines how trusted scoring data, extensive testing with third‑party sources, and open‑model transparency help address data‑quality challenges and prevent harmful or inaccurate AI outputs.
- AI Personalization in Tennis Media - Brian explains how AI enables fast, multilingual, personalized tennis storytelling for fans, dispels the myth that AI replaces creativity, and predicts its transformative impact on the sport’s content ecosystem.
- AI-Driven Tennis Storytelling - The segment highlights how IBM’s partnership with the US Open uses AI to streamline content creation, solve the “blank page” problem, and personalize fan experiences in tennis.
Full Transcript
# Generative AI Transforms US Open Experience **Source:** [https://www.youtube.com/watch?v=hwim1CYl0fI](https://www.youtube.com/watch?v=hwim1CYl0fI) **Duration:** 00:32:39 ## Summary - The episode explores how “openness” in AI is reshaping industries, with a focus on generative AI’s role at the US Open tennis tournament. - Brian Ryerson, Senior Director of Digital Strategy for the USTA, explains the organization’s mission to promote tennis as a health‑and‑wellness activity and highlights the US Open as its flagship global showcase. - IBM’s three‑decade partnership with the USTA now leverages the IBM Granite Family large language model, built on the watsonx platform, to automatically generate match insights, spoken commentary, and post‑match summaries for the tournament’s app and website. - These AI‑driven content tools enable the USTA’s editorial team to cover significantly more matches, delivering richer, real‑time experiences to the millions of fans worldwide. - The season’s broader goal is to reach over a million fans for the upcoming US Open, illustrating how open, generative AI can expand audience engagement at scale. ## Sections - [00:00:00](https://www.youtube.com/watch?v=hwim1CYl0fI&t=0s) **Generative AI Enhances US Open** - Malcolm Gladwell introduces US Tennis Association’s Brian Ryerson to discuss how IBM’s open, generative‑AI solutions deliver scalable match insights, spoken commentary, and post‑match summaries for millions of US Open fans. - [00:03:06](https://www.youtube.com/watch?v=hwim1CYl0fI&t=186s) **Digital Director’s Journey at US Open** - Brian recounts his path from a marketing and technology graduate and lacrosse player to becoming the US Open’s digital director, overseeing consumer engagement for a growing food‑and‑wine tennis festival. - [00:06:10](https://www.youtube.com/watch?v=hwim1CYl0fI&t=370s) **Crafting Real‑Time Sports Narratives** - The speakers discuss how storytelling drives fan engagement at the US Open, balancing planned narratives with unpredictable match outcomes to appeal to diverse audiences. - [00:09:17](https://www.youtube.com/watch?v=hwim1CYl0fI&t=557s) **IBM‑USTA Digital Partnership Highlights** - The speaker describes a 30‑year IBM consulting partnership that equips the USTA with digital tools and AI‑driven video highlights, turning lengthy tennis matches into three‑minute clips delivered to fans almost instantly. - [00:12:20](https://www.youtube.com/watch?v=hwim1CYl0fI&t=740s) **US Open App: Fan Guide Overview** - Brian explains that the US Open app serves as an on‑site companion for the millions of attendees, offering schedules, live scores, match previews, post‑match summaries, and integrated SlamTracker features to enhance the tournament experience. - [00:15:24](https://www.youtube.com/watch?v=hwim1CYl0fI&t=924s) **AI-Powered Tennis Shot Visualization** - Brian explains how AI can instantly render every ball’s trajectory with layered statistics, turning standard broadcasts into an interactive, data‑rich experience for fans and analysts alike. - [00:18:39](https://www.youtube.com/watch?v=hwim1CYl0fI&t=1119s) **AI-Powered Tennis Match Reporting** - The speakers explain how Watsonx generative AI transforms tennis’s rich structured and unstructured data into full‑scale, automated match stories, enabling comprehensive coverage and new fan outreach worldwide. - [00:21:45](https://www.youtube.com/watch?v=hwim1CYl0fI&t=1305s) **Ensuring Data Accuracy & Scaling Real‑Time Summaries** - The speakers discuss validating data sources using watsonx tools and continuous model retraining, then leveraging IBM Granite models to handle real‑time summary generation across 22 simultaneous courts. - [00:24:49](https://www.youtube.com/watch?v=hwim1CYl0fI&t=1489s) **Ensuring AI Data Quality & Risk Management** - Brian outlines how trusted scoring data, extensive testing with third‑party sources, and open‑model transparency help address data‑quality challenges and prevent harmful or inaccurate AI outputs. - [00:27:58](https://www.youtube.com/watch?v=hwim1CYl0fI&t=1678s) **AI Personalization in Tennis Media** - Brian explains how AI enables fast, multilingual, personalized tennis storytelling for fans, dispels the myth that AI replaces creativity, and predicts its transformative impact on the sport’s content ecosystem. - [00:31:01](https://www.youtube.com/watch?v=hwim1CYl0fI&t=1861s) **AI-Driven Tennis Storytelling** - The segment highlights how IBM’s partnership with the US Open uses AI to streamline content creation, solve the “blank page” problem, and personalize fan experiences in tennis. ## Full Transcript
Malcolm: Hello, hello.
Welcome to Smart Talks with IBM, a podcast from Pushkin
Industries, iHeartRadio, and IBM.
I'm Malcolm Gladwell.
This season, we're diving back into the world of artificial intelligence,
but with a focus on the powerful concept of open, its possibilities,
implications, and misconceptions.
We'll look at openness from a variety of angles and explore how the concept
is already reshaping industries, ways of doing business, and our
very notion of what's possible.
I'm particularly excited for today's guest, Brian Ryerson.
He is senior Director of Digital Strategy at the US Tennis Association, helping
to oversee one of the most iconic events in the world of sports, the US Open.
Brian sat down with Pushkin's own Jacob Goldstein, host of the
podcast, What's Your Problem?
A veteran business journalist, Jacob has reported for the Wall Street Journal,
the Miami Herald, and was a longtime host of the NPR program, Planet Money.
IBM has been the official technology partner of the US Tennis
Association for more than 30 years.
And the more recent evolution into generative AI has enhanced the world-class
digital experiences that help more than 15 million fans from all over the world
enjoy the US Open Tennis Championships.
In this episode, we will explore how generative AI is being used to generate
match insights, spoken commentary for match highlights, and post match
summaries at scale for fans to enjoy through the US Open app and website.
We'll explore how these AI solutions enable the editorial team to cover more of
the tournament than ever before, bringing fans even closer to the game they love.
And we'll learn more about one of the engines behind this AI-powered
content creation: a large language model from the IBM Granite Family,
which is trained and maintained using the watsonx AI and data platform.
Okay, let's dive in.
Jacob: Brian, welcome to the show.
Brian: Thanks for having me.
I'm excited to be here.
Jacob: Can you say your name and your job?
Brian: Yeah.
I'm Brian Ryerson, I'm Senior Director of Digital Strategy at the USTA.
Jacob: Dumb question, what's the USTA?
Brian: The US Tennis Association.
Jacob: And tell me about the USTA, what is it?
Brian: Yeah, so the USTA is the governing body of tennis in the US.
Our mission is to grow the sport of tennis across the US at all levels.
Really, I would say we're more of like a health and wellness company where tennis
is the means to health and wellness.
And then the US Open is kind of our tent pole event that happens
every year in Flushing Meadows, and is really our chance to showcase
the sport of tennis at its highest level to fans all around the world.
Jacob: Yeah, I mean the US Open, I assume most people know this, but it's a
Grand Slam, it's one of the, what, four biggest tennis tournaments in the world?
Brian: Correct?
Yes.
Yeah, every year, especially the past couple years, we've seen immense
growth, and we are very hopeful this year, and our big goal is to have
over a million fans on site during the three-week window this year.
So it's an amazing event.
I always say it's a food and wine festival where tennis is the main attraction, and
it's a really fun, unique atmosphere.
Jacob: How did you get into the tennis business?
Brian: It's a great question.
It's not where I thought I'd end up for, especially being there for 14 years.
So I was a marketing and technology major in school, and I also played college
lacrosse, and sports was always a big part of my life, and always wanted to be
in the sports and entertainment world.
I'm here from the New York area, this is where I grew up.
So I moved back home, and had a few friends who worked there.
And I started out more on the numbers side of things, and really digital
analytics, was really the start of when Facebook and Twitter was just starting,
and digital marketing and all of that.
And I went to my first US Open not really knowing what to expect.
And again, I think the atmosphere kind of captivated me and hooked me
in, and I've been there now 14 years.
Jacob: And so your title is digital director.
What does that mean?
What's your job?
Brian: Yeah, so it's an interesting one, because it's tough to explain to
folks who are not in the weeds on all things US Open or even in the sports
world, but really I oversee all of our consumer facing digital property.
So that's the usopen.org, our website built by IBM, as well as our mobile app.
I oversee our content strategy, our sponsorship integrations.
Really anything consumer facing that happens on the web is under my purview.
Even some of our new platform extensions and gaming and things like that,
anything that you can physically interact with is kind of under my purview.
Jacob: And so you've been there now for 14-ish years, which in
the digital world is a long time.
How has that sort of digital experience of sports changed over that time?
Brian: Yeah, it's obviously grown.
Digital now is, what we say and what my team says is, it's the number
one way to engage with fans that can't make it to the event, as well
as those fans who are at the event, and how do you enrich their stay.
So it's really kind of, you're tackling multiple fan personas.
It's the international fan who's staying up late to watch in other countries,
to the fan here who's maybe watching on broadcast and we go in to accompany and
enrich that broadcast with new stats and insights, to the onsite fan who
bought a ticket and maybe doesn't know what match is happening on what court.
We do have 20 plus courts happening at a time with all different matches, so
really try to help all fans navigate the US Open the best way possible.
Jacob: And so what are some of the sort of problems you're trying to solve?
What are some of the hard things about your job?
Brian: Obviously technology changes at a rapid pace, right?
So I think part of it is, how do we stay on the forefront of that, and how
do we do that in the best way and make the best fan experience possible, and
the best user experiences possible?
That's always kind of driving factor number one.
Then number two, it's understanding and listening to our fans and
what kind of content they want.
You'll hear me talk a lot about storytelling.
I feel like there's a lot of storytelling that happens around the US Open that
really, really want to bring to fans.
And that can be as simple as storytelling of what's happening today and what you
should be watching to, maybe it's your favorite players and what's going on
behind the scenes with them to, even introducing, I want to say the casual
fans to who they should be watching, why they should follow certain players, and
more bringing that player's story to life.
Jacob: Yeah, I mean I feel like almost the whole point of sports is to create
stories for us to follow, right?
They're engineered to be stories.
Brian: Exactly.
Jacob: This thing is happening in front of you, and there are two antagonist,
and the stakes are high, and you don't know how it's going to end.
It's built to be a story.
Brian: And that's the main challenge of the job is you can plan, plan, plan, but
once you get two players on court and you don't know what that outcome's going to
be, it's now sitting, and waiting, and watching, and you become a fan yourself,
and then it's, how do you really captivate that story, and how do you narrate it,
and how do you translate that to fans?
Jacob: And it's like you kind of have to do it in real time, right?
The whole point of sports is you don't know what's going to happen.
Brian: Exactly, and that's the excitement.
And it's also, there's so many different types of fans.
There's the fans who want a lot of enriched data, and their tennis nerds,
for lack of better of saying it, and that they really want to dive deep into
the intricacies of the game, versus the casual fan who maybe just wants more
of this high level storyline of what does this mean, why is it important?
So it's really trying to figure out how to deliver that at scale, and really help
fans get what they're looking for, and the type of content they're looking for.
Jacob: So are there specific examples of how fan feedback has led to specific
features, digital features you build?
Are there particularly popular features you've come up with?
What are some specifics?
Brian: Yeah, some low-hanging fruit type things that came from fan feedback is
simple things sometimes, like managing time zones of when matches start.
Jacob: A persistent problem for those of us who work across time zones, right?
Brian: Exactly.
And we do have, like I mentioned, 20+ courts happening at a time, so
it's a lot to follow, and how do you translate that to a fan, whether
it's to their native language or to their time zone or things like that.
So that's one thing that came through fan feedback.
And another one, a three to five hour match, especially when you're having 20+
of them happening at a time is, there's too much for one person to follow.
So how do you start from an editorial perspective really helping with that
storytelling and guiding a fan to like, all right, whether there's an upset about
to happen, or here's your matches to watch, or even some of the predictions
we're starting to put in is, we really want to guide the fan before a match,
here's where you should tune in, to even after a match of here's what's
happened, here's what's important.
And we're really excited with some of the features we've built in the last few
years that, I would say really helps us do that at more scale than what we were
able to do with just writers following a match and covering every single match.
Jacob: So I want to talk a little bit about the partnership
between IBM and the USTA.
Just tell me about the work you do together.
Brian: So IBM is our official digital and technology partner, and
innovation partner of the US Open.
They predate me, it's a 30-year partnership, and
it truly is a partnership.
So I view the IBM consulting team as an extension of my USTA team.
So we work with them year round, they design, develop, and
deliver the digital properties.
They help us provide the tools to create content, to do things at scale.
They help us from stats and information, and really help us
push from an innovation standpoint to make sure that we are staying
on that cutting edge of technology.
So I would truly say it is much more than a sponsorship, where
it's truly a partnership to deliver that fan experience.
Jacob: And so what are some of the specific things that
you have done with IBM?
Brian: Yeah, so I mean there's countless ones to talk through.
Obviously 30 years ago they helped us build our first website, and
it's kind of grown from there.
Over the past few years, I would say, I think it was 2018
is we started AI highlights.
So that was really when we were able to have all 20 matches going at a
single time, we were able to quickly deliver succinct highlights to fans
to our digital platform, so they could see highlights for every single court.
Jacob: Is that video highlights?
Is that text summaries?
What does that mean?
Brian: At the time it was video highlights.
So it was really taking that three to five hour match, let's say, and cut it
down to a three-minute highlight that could show up within moments after a match
ending to our website and our mobile app.
So fans could see that all around the world and really kind of get that three
minute overview, what happened in a match.
Jacob: And was that AI enabled?
Was AI a piece of how to do that?
Brian: It was, it was probably our first foray into AI back then.
Jacob: Well 2018 is relatively early.
Brian: Yeah, exactly.
Jacob: Early for tennis.
Brian: Exactly, yeah.
It really, I don't want to say opened up our ability to one, again,
story tell, but attract new fans too is, video has actually been our
number one growth area since 2018-
Jacob: Makes sense.
... Brian: and I think a lot of that has to do with the scale
of how we deliver that content.
Jacob: Using AI and being able to deliver the sort of video
highlight reels at scale.
Brian: Yeah, and do it quickly, right?
We've always had highlights, but it was a manual process where you
had a video editor cutting through a three-hour match, selecting the
right scene, stitching together, it would've to get voiced over, et cetera.
We really have used AI to make it, I want to say, much more efficient
and speed up that process, and deliver it more quickly to our fans.
Jacob: I mean, it would be a bummer to get scooped by whatever, NBC News
or ESPN or whatever, I'm sure they're all your partners and you love them.
Brian: Yeah, exactly.
Jacob: Obviously you want to have the video first, right?
It's your match.
Brian: Yeah, and I think it's also important to us as being the USTA
is ensuring that it's not just the main marquee player, it's that every
player in all those storylines, and that whether it's the main singles
draw to or mixed doubles, et cetera, they all need highlights, and they
all have their own stories to tell, and how do we do that at scale?
It was something that before we had that product, it was not
something we were able to do.
Jacob: Great.
So let's talk in some more detail about what you're working on.
Let's start with the app.
Tell me about the US Open app and the companion website.
Brian: Yeah, so I'll start with the app, and I feel like they serve similar
needs, but they're a little different in their own respective manners.
The app, everybody has a phone in their hands at this point.
The app is kind of their guide to, when I say a million fans on site,
we view the app as, we want that to be their onsite guide and companion.
Jacob: A million, let's just pause on a million fans on site, right?
Because like a big, professional, whatever, an NFL game or something,
that's like 100,000, this is 10X that.
Brian: Yeah, in a three-week window, in a very succinct,
tight, action-packed window.
There's a lot of action coming through.
Jacob: A lot of logistics.
Okay, so keep going.
Brian: Yes.
So the app, whether it's finding the schedules, the live scores,
what's happening on court, that's really the focus point of the app.
And what we're really focused on this year is, how do we build in some of
those match summaries into the app, into our SlamTracker experience?
So again, before a match, that kind of match preview of here's maybe...
If you have a ticket, here's what to expect, here's our likelihood to win,
who we are predicting, so you can kind of get some information heading in.
And then after the match it's more of, what just happened, what it means
for the rest of the draw, who they're playing next, is this the first time
this has happened, et cetera, and really enriching that experience as well.
So the app is one, your guide to what you should be watching, but
also then giving you that insights and context of what's happening on
that court as you're watching it.
Jacob: It's like the commentator in your pocket.
Brian: Exactly.
Jacob: So you used a phrase in there, as if I already knew it,
and I love the phrase, but I want you to talk more about it.
That phrase is SlamTracker.
Brian: Yes.
So SlamTracker is our longstanding live scores, I want to say match center.
It is where every single data point for every single match lives, and it really
helps showcase what's happening to match.
I say it's our broadcast companion.
So if you're watching live, it's our in-stadium companion.
It's also the best thing to have if you aren't able to watch.
Jacob: And so like I'm on the app and there's a thing called SlamTracker?
Brian: Yes.
Jacob: And I tap SlamTracker, what do I see on my phone when I tap SlamTracker
midday when the tournament's happening?
Brian: So before a match, that's where you get a lot of pre-match content, that's
where those live, kind of our predictions, our likelihood to win lives within that.
So likelihood to win essentially pulls in a bunch of data points, so pass matches
how many times the players have played against each other, even some punditry
and other written articles that maybe our editorial team put out, and really
kind of puts a prediction out there.
Jacob: And so it's just a percentage chance?
Brian: Yes, exactly.
But it uses millions of data points that come up with that
Jacob: Yes.
... Brian: so it really helps you understand what you're getting into for that match.
During a live match, it is every single point, so point-by-point scoring, as well
as in-depth analysis and point commentary.
Or also this year I have a live visualization that accompanies that, that
will really help bring the match together.
And what I mean by that is it uses our ball-tracking technology to really
showcase the match in near real time.
So within seconds delay of where the ball's being hit, where the players are,
and really bring a visualization to life, and layered stats and data on top of that.
Jacob: Is that sort of like, when I'm watching a match on TV and there's
a close call, is the ball in or out, and they do that thing where they
kind of show a sort of video game version of where the ball landed.
Does it look like that?
Brian: It's like that, but for every single shot.
So it's not just those close ones.
It's our first foray to bring that match to life.
Jacob: And so what do I see on that kind of view that I don't see
from whatever, watching the video?
Brian: Yeah, so one, you'll be able just to see more of the ball trajectory
and where the ball's being hit, but then you can also start layering things
in stats and insights on top of that.
So how many times has Player A hit the ball on a certain baseline?
How fast are they hitting it?
Maybe their served percentage at a certain side of the court, et cetera.
So you can really start layering in for the ones that really
want to dive deep into the-
Jacob: It's for the nerds, it's for the...
It's the information rich.
Brian: Exactly.
It's the strategy of tennis.
It really should be an interesting way to slice and dice a match.
Jacob: Huh.
Malcolm: It's remarkable how the USTA is leveraging AI to enhance
fan engagement and deliver immersive experiences both onsite and online.
Brian's emphasis on storytelling really underscores the
evolution of sports marketing.
The SlamTracker feature particularly caught my attention.
It's essentially bringing the excitement of a tennis match to
life in your palm moment by moment.
As someone who appreciates the narrative intricacies of sports, I
find it compelling how AI helps predict and analyze matches in real time.
Jacob: Tell me about the AI commentary feature.
Brian: Yeah, I know I mentioned AI highlights back in 2018.
It's now progressed for us and again, if we go back to before we had AI
highlights, to have a highlight ready for the site it was a video editor
cutting the highlight, it getting voiced over, and then being published to the
site, and it took probably an hour+ for that highlight to really be created.
Now with AI commentary, not only are we creating and cutting the highlights
using our AI technology, but it's now using all the data points that we have
around the match, whether it's our live scoring data, our ball trajectory data, et
cetera, and it's really creating a script to help story-tell around that match,
and that's all using watsonx technology.
And then using text to speech, we're able to actually then create the
commentary on top of that, which all happens now within minutes.
So our team's able to now create fully voiced highlights for
every men's and women's singles match to our site within minutes.
Jacob: So I know there's a new feature you're working on for
this year called Match Reports.
Brian: Yes.
Jacob: What are Match Reports?
Brian: It's our ability to succinctly tell the story of a match.
So everything that happens in five hours within that match, down to
a couple paragraphs that really helps a user understand or a fan
understand what just happened.
Again, some key stats, what's upcoming, really help us with that storytelling.
In the past, when we have 22 courts happening at a certain time, we would
have to pick and choose which stories we think, or which matches we think
are going to have the best stories, and that's a really hard thing to
predict from an editorial perspective.
With our match reports now, we'll be able to have full coverage of every
single match during the main draw.
Jacob: So of course I want to talk about generative AI.
How could we not talk about generative AI?
Brian: Of course.
Jacob: What are you working on with generative AI?
Brian: So Match Reports is the prime example of it.
So Match reports would be completely using watsonx generative AI technology.
And really, again, to us it's, how can we do that storytelling at scale?
Tennis is such a data rich sport.
All sports have data, but tennis has a lot of shots, and different shot
types, and ball trajectory, and live scoring data, and umpire chair data,
and crowd, and all of that factoring in.
Generative AI really helps us take some of that structured and unstructured
data, really one, organize it in a way, but then help us quickly tell
that story at scale to all of our fans.
And I think we're really just starting to scratch at some of the capabilities,
and we're really excited about where we're being, but we also see the
opportunity of even how we can grow to new fans, and new fans around the
world using generative AI in the future.
Jacob: I'm curious, and you alluded to this a moment ago, but I'd like
to talk a little bit more about it.
It seems interesting as a technical problem is, the nature of turning
tennis matches into stories, which is fundamentally what we're talking about
here in different ways and different media, is about taking both structured
data, like the stats points, stats matches, and also unstructured data
like commentary, and articles, and the kind of fuzzier parts of storytelling.
And so I'm curious how AI kind of helps you manage both the
structured and the unstructured data.
Brian: So I think the structured data is pretty self-explanatory, but when
you get into the unstructured data and some of the punditry, that's where you
get more of the opinion pieces into it.
Like a specific player matchup, this player always plays well
against so-and-so, or they always play well at night, or they're
a fan favorite and the crowd...
Adrenaline and the crowd being behind you can really motivate
you to play a lot better.
So it pulls in all those unstructured pieces and helps us really put some
more rigor around it, and help add and enrich our storytelling with it.
Jacob: And so I'm curious, when you're starting to use generative
AI over the past few years, what were your concerns going into that?
Brian: I think our biggest concern is ensuring that one, factually it
is correct, because it's only as good as the data you feed in, and how do
you really ensure that your model's working right, and that the output and
the data you're feeding it matches the output, and how do you do that at scale?
So we do have a lot of human intervention.
That's where the IBM consulting team, they're on site with us for those full
three weeks really helping us review everything and we're constantly learning,
especially early in the tournament.
And I would say the other big concern, again it goes around to
the data is, what data do we have available that is trustworthy?
So we are feel very confident with the data that comes off of court, but
when we get into that unstructured piece, what are the right data sources?
How do we validate those data sources, and how do we ensure that they're
accurate, because the data that has to go in has to be accurate for the output.
Jacob: So how do you do that?
That's the concern.
How do you address it?
Brian: Yeah, so I think there's a number of tools that we use,
all within the watsonx umbrella.
We do a lot of training with the IBM team, so we have to constantly
train and retrain that model.
I think the other piece that we're doing is, again, as we're creating that
content and we have the IBM consulting team on site helping us with that, is
as we see things and we see outputs, it's re-feeding that back into the model
to make it better for the next time.
So it's a constantly learning process that we're undergoing.
Jacob: So I want to talk about scale.
Brian: Yes.
Jacob: You have what, 22 different courts with matches going all at the same time.
You're trying to approximately instantly generate summaries of all these
matches in something like real time.
And I'm curious, in particular how the IBM models you're using, the IBM
granite models are helping you scale?
Brian: Yeah, so I think one of the big learnings we had with IBM granite
models too is that we're able to run it against last year's tournaments
and see what the expected outputs could be, and really help train that
model heading into the tournament.
Because as we talked about in the beginning is, we can plan, plan,
plan, but once two players get on court, the outcome is unknown.
So how do we really run it through its paces, and really make sure that whatever
that outcome could be, and whatever that scenario is, whether it's a fifth
set tie-break that happens, or maybe there's a fault at the end the match or
something that we're not anticipating, that we have that accounted for, and
that the A won't throw off that output.
So we really try to think through every scenario, which is sometimes difficult
because again, live sports is the unknown, is the unknown, that's what makes it fun.
We do spend a lot of time thinking through potential scenarios, and
ensuring that we have the right data sets and the model to predict that.
Jacob: Tell me about Match Reports and the generative AI model you're using for that.
Brian: So Match Reports will be new for us this year, so we're in testing right
now, so we're really excited around it.
But the model that we'll be able use using watsonx will use a bunch of
different parts of the suite of tools, meaning that again, taking some of
that punditry and the unstructured data and the editorial spin, it'll
take our structured data as well.
And really what we're working on right now is figuring out the right
prompts for the AI to really ensure that it tells the right structured
story, meaning what just happened.
So a recap is pretty standard.
Here's what the data's telling us, who won, who lost how many sets?
Here's the score.
Jacob: That's the structured data part.
That's the easy part.
Brian: And then really where it gets exciting is then, what does
this mean, meaning, what's upcoming?
So there's all these different scenarios when you get into 254
players and a large draw, this allows us to distill that down and really
tell what could happen upcoming.
The AI helps us do that at scale.
Jacob: So I want to generalize for a moment to talk about broader challenges
with AI and how you've solved them.
A lot of generative AI pilots fail because the data quality isn't high enough,
because the risk controls aren't there.
And so I'm curious how you dealt with those problems, and are dealing with them.
Brian: Data quality, again, we feel calm with the data that is supplied from
the US Open and from the USTA, right?
So we have, again, that's our structured scoring data and all of that.
I think what we're constantly looking at is when we get outside of
our known sources and out to third parties, is that's where a lot of
the testing and model work happens.
So we pull in different data sources and really try to work
through how it changes that output.
Again, some of that comes down to where it's an open model and the
transparency that we have, and the learning that comes behind it.
That's where a lot of that confidence can come from, and it comes from a lot
of testing and feeding it more data.
Your second question was a little bit more around the output, I believe, right?
Jacob: And risks, right?
So risks, I think of risks more in terms of output, right?
Brian: Yeah.
Jacob: The obvious fear is like, what if it says something wrong,
or inflammatory, or whatever.
That seems scary.
Brian: Yeah, it definitely is, and it was definitely one of our largest
concerns when we first took this foray.
I would say a lot of that comes through our work with IBM and the IBM
consulting team, and really ensuring that, again, they're an extension in
the partnership there of our team.
So whenever we are creating, let's say it's the Match Report, and we're
going to be creating these succinct articles for every single men's and
women's single match that happens, is all of those will have manual review,
and people looking through them for accuracy to ensure that the model
didn't hallucinate or make up a fact, or fill in the gaps and things like that.
That's the first step.
And then also when our editorial team goes to publish those to the website,
they're going to be checking it as well.
So there are manual interventions throughout that to really check that
model, but we feel that the ability to do it at scale and with us more to
check that, is the efficiency problem that we've been looking to solve.
Jacob: So the USTA and IBM have been working together on digital innovation
for like 30 years, from the first website for the USTA until now.
So that's the past 30 years.
If you look ahead, what's the next 30?
Brian: 30 years is a really long time.
Jacob: How about three?
Brian: Yeah.
I think where I get excited, and I alluded to it in the beginning about
how I feel like we're just scratching at the surface, especially with generative
AI and where I see it going is, there's a lot of different fans out there.
And we're also very cognizant of the US Open that we're a worldwide event,
and that there's a lot of different fans that we're not necessarily
creating content for bespoke.
Meaning, in their native language, or maybe it's in that native player's
language, and things like that is...
Where I get excited is we've seen immense growth with AI highlights, and the
ability to now do highlights at scale is the ability for us to start creating
content in different languages, maybe covering different parts of the match.
So maybe you do have that stats junkie who really wants just, it's the fastest
serve and here's the deep insights, versus the casual fan who's looking
for more of the storytelling around how a player trains, and what leading up
to it was like, and what it means for them afterwards, and things like that.
A lot of that takes a lot of time.
Now we're able to solve that efficiency problem and do it in multiple languages.
We can really create, I want to say personalized content to a lot more
fans all around the world which, again, helps us grow the sport of tennis.
Jacob: Great.
So I want to finish with the speed round.
Brian: Okay.
Jacob: Are you ready?
Brian: I am ready.
Jacob: Okay.
First thing that comes to mind, complete this sentence.
In five years, AI will-
Brian: Transform many parts of the business.
Jacob: What is the number one thing that people misunderstand about AI?
Brian: That it's supplemental, not replacing.
Meaning that it helps with efficiencies, but it doesn't necessarily
replace the creativity right now.
Jacob: What advice would you give yourself 10 years ago to
better prepare you for today?
Brian: I think it would've been, especially now that we're able to
take so much of that unstructured data and pass content that we...
Were created to help tell stories, was to, I want to say archive more
of that in a way that we could be using that to help pull from that now.
So we've seen kind of a change in the guard from some of our star
players to now new and up and comers, and it would be really fascinating
to me if there was a way to cross section some of that and saying what
trajectories are certain up and coming players may be following from others.
So it's more, I wish we kept more of the content we created back-
Jacob: Save the data.
Brian: Yeah, exactly.
Jacob: That's what you're telling yourself, save the data.
Brian: Exactly.
Jacob: Well, are you saving it all now?
Brian: Oh yeah, 100%, we learned our lesson.
Yes, yes.
Jacob: Okay.
So on the business side of AI, what do you think is the next big thing?
Brian: I alluded to it earlier.
I think it's personalization and getting content that's catered to
you at scale, whether that's across the sports sphere, or any type of
written content or news content.
I feel like the ability to really get [inaudible] to the type of
fan you are and the insights you have is where we're all headed.
Jacob: And in terms of your non-work life, how do you use AI day to day?
Brian: It's funny, I was just having this conversation with a friend the
other day and we were talking about that sometimes when you're starting
something new, the hardest thing to do is you have a blank piece of paper or
a thought, and how do you get started?
Sometimes with these generative models, the easiest thing and the best thing
you can do is it helps you get started.
Meaning it may not be a hundred percent with that first prompt, but
it's that efficiency of, whether it's an outline for a new idea, or it's
a marketing brief you have to write.
Or sometimes even if it's an email you have to write for a personal something
and you're not sure how to word it the right way, it allows you to have a
start, and then you can edit from there.
So again, going back to my efficiency point, it helps you become more efficient.
Jacob: It solves the blank page problem.
Brian: It does.
Jacob: Brian, it was great to talk with you.
Thank you so much for your time.
Brian: Yeah, this was fun.
Thanks for having me.
[MG OUTRO]
Malcolm: A huge thanks to Jacob and Brian for the deep dive into
the cutting-edge innovations transforming the game of tennis.
Brian shed light on how the US Open’s Partnership with IBM is
harnessing data-driven insights to reshape storytelling in sports, from
AI-generated commentary to match reports.
As we look ahead, I’m excited about the possibilities for personalizing
content and reaching fans in new ways.
The future of AI promises more than just efficiency—it's about
enhancing fan experiences worldwide.
[END CREDITS]
Smart Talks with IBM is produced by Matt Romano, Joey
Fischground, and Jacob Goldstein.
We’re edited by Lidia Jean Kott.
Our engineers are Sarah Brugueire [Brew-Ghare [hard G!]] , and
Ben Tolliday.
Theme song by Gramoscope.
Special thanks to the 8Bar and IBM teams, as well as the Pushkin marketing team.
Smart Talks with IBM is a production of Pushkin Industries
and Ruby Studio at iHeartMedia.
To find more Pushkin podcasts, listen on the iHeartRadio app, Apple Podcasts,
or wherever you listen to podcasts.
I’m Malcolm Gladwell.
This is a paid advertisement from IBM.
The conversations on this podcast don't necessarily represent IBM's
positions, strategies or opinions.