June 3, 2026 • 48 mins
Most of what happens inside the UFC Octagon is too fast for the human eye to follow. Enter Alon Cohen, Executive Vice President of Innovation for TKO, who has spent 15 years building the data and AI systems that expose the hidden moments that help decide a match. Malcolm Gladwell sits down with Alon to uncover how UFC’s partnership with IBM turns chaos into clarity, giving fans and commentators a deeper story behind every bout.
This is a paid advertisement from IBM. The conversations on this podcast don’t necessarily represent IBM's positions, strategies or opinions.
Visit us at https://www.ibm.com/think/podcasts/smart-talks
See omnystudio.com/listener for privacy information.
Listen
Watch
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Speaker 1 (00:00):
Hey everyone, it's Robert and Joe here. Today we've got
something a little bit different to share with you. It's
a new season of the Smart Talks with IBM podcast series.
Speaker 2 (00:09):
This season on Smart Talks with IBM, Malcolm Gladwell is back,
and this time he's taking the show on the road.
Malcolm is stepping outside the studio to explore how IBM
clients are using artificial intelligence to solve real world challenges
and transform the way they do business.
Speaker 1 (00:25):
From accelerating scientific breakthroughs to reimagining education. It's a fresh
look at innovation in action, where big ideas meet cutting
edge solutions.
Speaker 2 (00:34):
You'll hear from industry leaders, creative thinkers, and of course
Malcolm Gladwell himself as he guides you through each story.
Speaker 1 (00:41):
New episodes of Smart Talks with IBM drop every month
on the iHeartRadio app, Apple Podcasts, or wherever you get
your podcasts. Learn more at IBM dot com slash smart Talks.
This is a paid advertisement from IBM.
Speaker 3 (00:57):
I'm Malcolm Gladwell and you're listening to Smart Talk with IBM.
Most of what happens in a UFC fight is too
fast to see. A fighter drops their shoulder for a
split second. Did you catch it? A shift in position
that looks insignificant but changes everything? Were you watching alone?
(01:17):
Cohen is the head of R and D for UFC.
His job is to help people see those moments, not
by slowing things down, but by knowing what to point
to after it happens. By the time you realize something mattered,
his data systems have already figured out why it's taken
fifteen years to get here, first with paper scorecards and
a TVO, now in partnership with IBM, and along the way,
(01:42):
a loan's learned something that applies far beyond fighting. The
best technology is the kind you don't.
Speaker 4 (01:49):
Notice at all.
Speaker 3 (01:50):
It just helps you see. I thought you were going
to be like tattoos muscle shirt. I thought you were
going to like I thought you were going to represent
the brand in that respect that you yourself would be.
It would be a kind of, you know, mixed martial
arts type. You were not, in fact a mixed martial
(02:11):
arts type.
Speaker 5 (02:12):
I did a little taekwondo in my past. I am
I am not in the way that you put that,
not a mixed martial arts type. But I think if
you if you come through the building in Vegas. If
you come through the building when we do a show,
you're going to see a lot of the mixed martial
arts type. It even surprised me. I came out of
the tech world, the young tech world in the two thousands,
(02:34):
and everybody was talking about, you know, we have to
have a mix of viewpoints and a mix of you know,
people from all walks of life, and all of these
other things that evolved into into something else. But yeah,
that didn't happen to me until I went to work
for UFC, which is like a weird way to get there.
Speaker 3 (02:49):
Were you in a tech world before? What were you doing?
Speaker 5 (02:51):
So when I left school, I went to a startup
that today we would call a big data company, and
it was there at a moment where everybody was doing
relational databases and relational databases from micro Strategy and from
Cognos and from whoever. So we did that two thousand
and one hits after I graduate nine to eleven and
(03:12):
the dot com bust and all that kind of stuff,
and we all looked at each other and we said,
no one, no one of these institutions that needs this
kind of information is going to take a risk on
a small company right now, they're going to retrench.
Speaker 4 (03:23):
And I went to law school.
Speaker 3 (03:26):
Oh, I see, you started tech. You briefly have a
foot in the twenty first century, and then you decide, no,
I'm going to go get a law degree.
Speaker 4 (03:34):
I did.
Speaker 5 (03:35):
People said, you feel like somebody who would benefit from this,
and I wanted to want it. And the first attorney
I worked for out of law school, he looked at
me and he goes, you need to go be in business,
like you're not an attorney.
Speaker 3 (03:50):
Yeah, so you're you're a failed lawyer. They kick you out.
Where do you go next?
Speaker 4 (03:56):
So that's what happened.
Speaker 5 (03:57):
So in two thousand and eight, there were a bunch
of lawyers who were doing just fine, but the bottom
has fallen out of the legal market. I was helping
a friend off the side of my desk who had
come to me with a banker's box of paper and said,
I have been watching The Ultimate Fighter, the reality show
where they pick new entrance to the UFC, and I
had been watching. He was a sports writer before, and
(04:18):
he very much. This gentleman's name is Romick an hour
romy comes to me and he says, there's no stats
for this stuff.
Speaker 4 (04:25):
I'm used to writing about baseball.
Speaker 5 (04:26):
So I did a full regression analysis after watching one
hundred hours of fight time, and now we're at closer
to two hundred hours of fight time. And I've been
scoring these fights, and the UFC's talent have been reading
my blog and they want me to do analysis for them,
and I can't be doing it on paper. And so
he came to a technologist and said, what do I do?
And we talked about double king the data in Indonesia
(04:47):
and building a database and APIs. A year later, we
were making small salaries and we had gotten this thing
up off the ground and going, and the UFC was
starting to use our statistics, and we had turned it
into a real data product. You know, we were able
to score electronically at that point. And the rest is
at this point seventeen or eighteen years of history.
Speaker 3 (05:06):
So wait, back up, this is really interesting. Pretend I
know nothing about UFC. Okay, So Romi comes to you.
And Romy's issue is what that the way in which
these matches are scored is too subjective.
Speaker 5 (05:20):
The way that these matches are scored is inscrutable to
the average person. So his analogy, and it's the one
that he experienced is when you write a summary of
last night's baseball game, right, what do you do?
Speaker 4 (05:33):
You say, here's my thesis statement.
Speaker 5 (05:36):
So and so had a great outing, and middle relief
collapsed or whatever it is, and last night at seven
pm at this stadium, the following happened. Here was the
final score. And then this middle paragraph is, you know,
middle relief had this as a cra and so on
and so forth, and you'd run an analysis and then
you talk about, you know, so and so has been
performing well and he had this outing and that outing
and blah blah blah blah.
Speaker 4 (05:55):
This is part of a trend.
Speaker 3 (05:56):
You tell the story of the game and the context
of a core of statistical.
Speaker 5 (06:01):
Knowledge exactly right. And this is at least how he wrote.
And you get to that paragraph in an MMA story
and it's non existent. It's so and so is a
strong striker. So and so is coming off of two losses,
so and so is on a three fight win streak.
And that is the totality of what's currently available. And
Romy's approach is we can count everything, but everything's not important.
(06:25):
And you can't count everything practically because by the time
he gets to the end of this first iteration, we
have sixty seven data points per fighter per round.
Speaker 4 (06:33):
So it's a ton of stuff.
Speaker 3 (06:35):
At this point, you're collecting the data.
Speaker 5 (06:37):
How just visually, he has a piece of paper and
he is on a TVO. Remember TV's. We had TV's
until long after they were dead because we needed them.
And he is playing and pausing and rewinding to be able.
Speaker 3 (06:48):
To He's doing it the way people in the olders
in baseball, remember they would score. Sure, they would take
the piece of paper and they would score the game
as they were watching. It's flowing to matches.
Speaker 5 (06:57):
His history is I go to baseball games with dad.
Dad has a scorecard, and you, as a kid, are
both drawn to it and averse to it because you're
like dad, you're missing the game, and at some point
you find yourself marking down the scorecard.
Speaker 4 (07:09):
And he brings a lot of that to this.
Speaker 3 (07:12):
So you say in his first iteration he had seventy
two data points, say that again, sixty seven sixty seven
data points per fighter fighter per round per round.
Speaker 4 (07:23):
Yeah, so that's.
Speaker 5 (07:24):
Consistently there or this as an average of Well, so
at any points on the sheet, there are sixty seven
different things that we are tracking. So there may be
more head strikes landed, powerhead strikes landed, and there may
be some other head strikes landed, but there's probably not
necessary tight submission or a camorra or something like that.
But these are different kinds of submission types that we
(07:45):
would track, and so all of them are available on
the sheet so that you can just tick those off
and move on. Right, So those are the sixty seven
independent boxes on the sheet that we could mark something
down on.
Speaker 3 (07:55):
Give me examples of things that non obvious things that
you would learn if you did a formal statistical analysis
of a match, like as a viewer or as a fan.
How is this enhancing his experience of what he's watching.
Speaker 5 (08:08):
A couple of things are happening inside of an MMA
match that are worthy of note to the average fan.
It is scored per round. And one of the problems
that you have when you score per round is that
people don't think per round right. They don't get to
the end of round one and say round one is over.
I will make a decision about round one, let us
now go to They don't do that. They look at
(08:29):
the totality of the match. The shorthand I used for
this for a long time is you make the invisible
visible to people like.
Speaker 4 (08:36):
What exactly did I see?
Speaker 5 (08:37):
The other thing that the last thing that the numbers
do for us is they tend to combat recency because
you just forget what happened in round one or it
just doesn't leave as strong an impression. And one of
the and of course fighters fight to that what do
you do right at.
Speaker 4 (08:51):
The end of the round?
Speaker 5 (08:52):
You take a dude and you take him down because
you were going to finish the fight now because you
wanted to leave in the impression and the impression in
the mind of the judges like that do you controlled
that round? And so you were trying to score these
big shots at the end of a round, and the
numbers allow us to battle some of that for our
fans to say, like, how well did he actually do?
Speaker 4 (09:10):
What did she actually do in this thing?
Speaker 5 (09:12):
So that's one of the big learnings is you're able
to go back in time and not have to watch
the video. You just get a spot to be like, oh, yeah,
there are two takedowns in that first round.
Speaker 3 (09:21):
And so you're allowing people to construct a much more
complete and accurate narrative of the of the match.
Speaker 5 (09:28):
I think so yeah, And I think for new fans
there's a different calculus because new fans don't know how
to watch the sport. And when you it's I joke
that when we all watch the Olympics, like, I don't
know anything about synchronized swimming and I shouldn't pretend to,
but the Olympic broadcast allows me to pretend to, right,
(09:49):
And that's a little bit of what's happening here is
that they can look at this and say, oh, I
get it right, Like I'm watching all this action, and
then we condense that down to this is the number
of like kicks this person landed, and they're like, oh,
I did see Okay, Now I know to focus on that.
This is part of the storyline and it is a
signpost and that's a big deal.
Speaker 3 (10:08):
So in the beginning, you're just a contractor with UFC.
Speaker 4 (10:11):
We are a contractor entity.
Speaker 2 (10:13):
Yeah.
Speaker 5 (10:13):
For the first seven years of our existence, we are
independent and are the official data feed of the UFC.
Speaker 3 (10:19):
And and at a certain point UFC says, come and
join the.
Speaker 5 (10:25):
Ari emmanual at wm IMG at the time buys UFC
and he says, I want to sell the data.
Speaker 4 (10:31):
Where's the data?
Speaker 5 (10:32):
And they said, well, these two nice kids in the
Georgetown waterfront they have the data, and he goes, what
do you mean they have the data? Like, it's our data,
and that started an acquisition. Conver We were a fold
into that larger acquisition.
Speaker 3 (10:43):
Going back to the fights, the data, how is it?
How is the scoring working at this point?
Speaker 4 (10:48):
So the tvo I brought up earlier, you're able to
watch it with slow moo and rewind and we have
at the time tablet or a touch screen, and we
have taken our piece of paper and we have split
it in twain and you're able to mark what you
see as you see it, save around you score.
Speaker 3 (11:03):
You've got trained scores, yes, yeah.
Speaker 5 (11:06):
They are some of my favorite people. We have had
trained scorers in our group that go back thirteen years
with us, folks that we plucked out of the ether. Right,
you put something online looking for people who are interested
in learning this stuff, and then you have to whittle
out the people who can learn how to do it
and then do it quickly. The first time you score
something like this and try to make sense of the
scoring page, it's going to take you fifteen minutes to do.
(11:28):
A five minute round might take you more. And that
means that at the end of the fight, you're probably
thirty five minutes late. And so you have to do
this for six or seven months on a regular basis,
paying you make sure that you know you're fairly compensated
to get you to the point where you're able to
make decisions rapidly. It just comes as second nature to you.
And this is the dirty little secret of UFC. But
(11:49):
we joke, we've been trying to put ourselves out of
that business for at this point eleven or twelve years
and we aren't close yet.
Speaker 3 (11:57):
Put yourself out of the business of having to rely
eye on a human score, a human score.
Speaker 5 (12:02):
Yeah, and we said that joshingly. But there's a sense
of which there's a sense in which at some point
you understand that compute ought to catch up with you, right,
And we said we should be out ahead of this
and sort of the Netflix model, Right, if DVDs are
going to be a problem, you shouldigure out what's coming next,
and you should do that also and disrupt yourself. And
(12:24):
you know, we wanted initially we have used it as
additive data, so we wanted to do motion tracking. So
eleven twelve years ago we bought a motion tracking software
and it couldn't make sense of any of what it
was seeing inside the octagon, like it really couldn't understand.
And this wasn't even striking. This is just like red
is here, blue is here, and the rough is here.
And so we taught a human system how to do it.
(12:44):
But we keep going back to the to the machine well,
hoping it will get better. And today, in fact we
are we are closer than ever, but nowhere near close
to overtaking us as scores.
Speaker 4 (12:55):
It's weird.
Speaker 5 (12:56):
I have been playing, as I said, with my motion
tracking computer vision experiments. We're twelve years ago. Ten years
ago I was hanging cameras to attempt to do a
skeletal tracking to see what that could give us, and
it didn't work. You know, we have been on a
ten year journey to discover what it can do and
being fostering of it. Right, That's what R and D
(13:20):
is supposed to say when something fails, to say, well
is there something of this that I can retain? Does
this add some value enough that it really makes sense
to just continue to invest in it some so if
it can ever make good on its promises, we'll get
to see exponentially.
Speaker 3 (13:36):
What striving you here is what you want to get
your data quicker? Or do you want more data? Do
you want qualitatively different data?
Speaker 2 (13:43):
What is it?
Speaker 3 (13:44):
What's what's what's in the back of your head?
Speaker 5 (13:46):
So man, so many motivations are pushing this for us.
One motivation is faster data. So imagine the following very simple.
If I see a significant strike landed in the middle
and so well, let's say the first person to one
hundred significant strikes landed in this fight, that is potentially
betting data. Somebody could bet who could get to that first.
(14:07):
Right now, I can only offer that data unofficially because
my humans need to wait for my official data to
come in. If computer vision could really get that right,
then I could stand behind that number and say that
is betting ready, and you could resolve that bet at
the moment it happens. And so you open up all
of these markets for one like that. That's a big
(14:28):
motivator for this kind of stuff. The second is I
am When I'm adding these AI technologies, I'm often looking
at them and saying, like, what else can I do
with this? What else is it telling me about the
fight that I'm not already getting motion was a big
one of them. Right, where are people in the octagon?
What I mentioned earlier that one of the one of
(14:49):
the criteria for judging a fight is control of the
octagon space. Well, okay, everything I was tracking with my
scores before doesn't talk about that.
Speaker 4 (14:56):
Right.
Speaker 5 (14:56):
If I'm hitting you more and you're you know, defending
poorly or whatever it is, maybe that's control. But what
if you're a counterpuncher, right, famous fighters who are counterpunchers.
I draw you in and then I hit you. Does
that mean I'm seating control to be able to take
back control?
Speaker 4 (15:10):
What does that mean?
Speaker 5 (15:11):
And so we didn't have any any numbers on where
people are. That's an immediate use of AI that is
additive to what I am doing. And all of this
is always in the service of storyline. Right, what is
not being captured in the fight? And what should the
commentators be talking about? And how can I support what
they're talking about? How can I give them something that
(15:32):
makes them think, Oh, actually, the thing I want to
be talking about here is this, Right, that's ultimately the
goal the goal here is I mean, let's go back
to the first thing you said. You said, I don't
look like the kind of person who might be an
MMA fan. There is a point at which if I
throw up a number on the screen and it's like,
this person is twenty seven point two four, and people
(15:53):
are like nerd, like, what are you doing? And there
is a space for that in other sports, but sometimes
we're doing it just to seem to technical. I think
if you're doing the tech right, you should forget about
the tech. You should forget about the fact that there's
AI behind that. You should forget about all of this.
The thing that hits the screen is so and so
has never lost a fight if they have landed four takedowns.
(16:17):
We're on number three. Right now, we know what we're watching. Yeah,
right now you have a binary, simple thing to look at.
So and so has a takedown accuracy of ninety four percent.
So and so has a takedown defense of seventy five percent.
Let's see how they match up against their classic averages.
And now you're getting into some more tech and number
you're like, this guy is below his average and that
(16:38):
guy's above his average. Okay, now we have a way
of measuring very quickly who's winning and who's losing. Across
at least this part of the fight, and so the
goal is to get to storyline as fast as possible
in human understandable terms. Right, This is in some ways
the great moment of the LM as well. Right, Who
cares how many weights and how many parameters and how
(16:59):
many whatever? When I talk to it, it feels like
I'm talking to a human. That's the great unlock. The
technology suddenly disappears and the experience stays. And that's at
our level, at our level of sophistication, that's what we're doing.
Speaker 3 (17:14):
Yeah, I want to go back to make sure I
understand when you talk about control of the octagon of
the octagon conceptually, what is control the octagon mean?
Speaker 5 (17:26):
It is the last of the criteria in the judging rules,
and it should mean that in a fight one of
the things you're trying to do is assert dominance the
most basic level.
Speaker 4 (17:40):
It is left vague.
Speaker 5 (17:41):
Different commissions around the country will tell you slightly different
things about what it means. Some of them will boil
it down to if I hit you more, I control
the fight, but a lot of others of them will
say it is really there to be that sixth sense
feel of was I able to put you where I
wanted you to be when I want you to be there,
(18:02):
and in our statistics, one of the ways you can
talk about that is advancing or center control. If I
always own the center, you always have the wall at
your back, so I control the space.
Speaker 4 (18:15):
Right.
Speaker 5 (18:15):
There are ways of finding small analogus directional pointers to
tell you that. But when you talk about what a
judge is looking for, they're looking for that ephemeral sense
of you know, who's the big.
Speaker 3 (18:31):
Dog, and that is if you're strictly kind of scoring
the match, that's one thing you're not picking up because
you're too focused on position, who's striking whom that kind
of larger gestal you're talking about a gestalt of right, Sure, yeah.
Speaker 5 (18:47):
Somehow the Novata State Athletic Commission to get to criteria
five and go gestalt.
Speaker 4 (18:52):
That's what we're looking for.
Speaker 5 (18:53):
We're trying to deal as a as a as a
matter of course, we want to bring people into our arena.
Have the six it's be devoid of Weltschmertz and focus
on the gestalt.
Speaker 4 (19:03):
And it just didn't. It didn't make it, That's what
I'm saying.
Speaker 3 (19:06):
So you've got your motivations are one I can enhance
the viewer experience in terms of story. Yep, I can.
I can facilitate things like betting on the on the match,
and I can aid the judges in getting a sense
of who the dominant party is.
Speaker 4 (19:25):
One and two.
Speaker 5 (19:25):
Yes, three, we actually scrub all of our all of
our video feeds into the arena, a scrubbed of our statistics.
I do not want the judges. Their job is to
follow the criteria set by their commission. So we're in
this weird spot where like my sport has, my fighters
are independent contractors. It's a regulated sport by the state
(19:47):
commission that we're dealing with, and my job is to
is to bring the event together. And as a result,
I don't want anyone pointing at us saying you said.
And so I decided we're like, look, you understand your criteria,
you're fully trained, judge. You need to decide who won
this fight. Our statistics will tell the story our statistics
tell and by the way, we can have an occasionally
antagonistic relationship where we thought that was a poor decision, right.
Speaker 4 (20:11):
Yeah, that makes it interesting exactly. Yeah.
Speaker 3 (20:13):
So okay, let's go back to the AI. So you're
you start experimenting with this a while ago. Oh yeah,
and you're not you're not entirely happy with the with the results.
Is that a fair or you're Oh, you understand it's embryotic.
Speaker 4 (20:28):
Both, right?
Speaker 5 (20:29):
You? Why should I start down the project of making
this work if I don't believe it's going to work?
Speaker 4 (20:35):
Right, I try?
Speaker 5 (20:37):
If I'm going to bother dedicating the time and the
effort and potentially a lot of money. I wanted to work. Uh,
and I was disappointed in time and again, and I
have found things to bring along right, So early skeletal
tracking has become the basis for today.
Speaker 3 (20:50):
SAT tracking is defined.
Speaker 5 (20:53):
The term skeletal tracking is when you hang cameras. Nowadays
you are very quickly able to discern what is is
not a human inside of your space, and then you're
able to identify points on their body, nowadays more points
than we used to.
Speaker 4 (21:07):
It used to be like.
Speaker 5 (21:08):
Shoulders, head, torso, hips, knees, feet, right, and nowadays you
have two additional points on the feet so you can
see their orientation. Hands you can see the orientation, and
face you can see where I'm looking. Those are basic
skeletal models and you need that to be able to
understand from an AI perspective, who is striking and was
(21:30):
that a miss?
Speaker 4 (21:30):
Was that a hit?
Speaker 5 (21:31):
We can get into collision detection, which is very difficult
because skeletal tracking isn't it's not the outside of your arm,
it's the inside. And then beyond was there a collision,
we get into problems of intent. So intent is the
hardest thing actually to solve. There's a lot of times
where two guys are fighting and one guy's going like this,
he's range finding, just putting a hand out there to
see is you know, how far away are you and
(21:54):
sort of to bat you away? And that is not
a strike attempt. How do you teach the computer that
that's not a strike attempt? Because sometimes it looks like it,
sometimes it doesn't. And then same thing with kick to
the head. It makes contact with the outset of my arm,
which I brought up in our world, that's a blocked strike.
(22:15):
But teaching a computer what exactly that means and when
and how like when it's up here, when my arm
is up, that's a block. When my arm is down
and hits my shoulder, that's not. It's those nuances that
proved incredibly difficult for machines to be able to handle
for a very very long time. And the acceleration in
the last few years which has allowed us to onboard
(22:36):
this technology has solved so many of these problems. At
the same time, we no longer need fixed cameras. I
now do it off the broadcast cameras, which are on
people's shoulders and they shake and they rotate and whatever
doesn't matter. It can still figure out what it's looking at.
This is the octagon, These are the fighters. Here are
their bodies, that's the ref He doesn't matter all of
that stuff. It can now figure out. It can begin
(22:57):
to understand what real landed myst is, and it can
do so on much less perfect data than we needed
the first time. That acceleration has been incredible. If I
didn't know step one and two and three and four,
I'm not sure how ready I would have been for
where we are now.
Speaker 3 (23:12):
Yeah, So let's just dig into where we are now
a little bit. So you go. I'm interested in the
partnership with IBM and the kind of transition from this
period of experimentation to where you are now. So where
at the time you guys, you're aware of.
Speaker 4 (23:30):
The development of AI yep.
Speaker 3 (23:33):
And it's getting better and better and better and better
and better, and you clearly have an intuition that, oh,
this is this could potentially really open some opportunities for us.
Speaker 4 (23:43):
Yep.
Speaker 3 (23:44):
What's the point in time where you start to think, oh,
this could be real.
Speaker 5 (23:49):
Our relationship with IBM is born of a little bit
of suffering on our behalf, is the best way to
put it. We had a partner as part of the
larger business that really wanted to focus on AI with us,
and we said, we would really like to do an
insights engine. We think it's really additive. These storylines in
real time would change the way that we talk about
(24:10):
the sport in broadcast. And for two years we went
down that road and it crashed and burned. We go
into the reasons, but they didn't understand the sport. They
tried to brute force the problem. And if you try
to brute force this problem, it's going to kill you.
And because there are just so many permutations out there,
(24:32):
and IBM starts a conversation with us, and very quickly
as we engage, a couple of things emerge, and they're
not about the tech. They say to us, we think
we can do it with the tech. We say, we
have to believe you that you can do it with
the tech. We don't know, we're not experts in it.
They can bring people who understand sports analysis to the table,
(24:53):
so all of a sudden, when my phone call ends,
when somebody at IBM has a question, they can talk
to somebody better. Yet, within the first of weeks, I said,
it would really be helpful to have somebody who's an
MMA fan, because some of your questions are specific to
the sport and we could answer them all the time.
But I think that the velocity here goes up if
you can just say, hey, Brad, what's happening here? Can
(25:15):
you explain what is the culture, what's important, what's not important? Right,
because you can come up with a lot of ideas
and fans will be like, I don't care, and it
gets worse from there.
Speaker 4 (25:24):
So we quickly eliminated that. With IBM.
Speaker 5 (25:27):
They had people on the bench who understood just the
area and then the specifics of our sport, and they
were able to fill in some of the gaps for us,
and so we could move at pace. And it was
all about the people at the beginning, and obviously beyond that,
they had to make good on the arctech and actually
do this. We can use the AI. It's not so
much that the AI needs to run the final product.
(25:48):
That's not what we're talking about. It's can the AI
speed up the creation of the product? Can AI help
us expand its reach? Can AI suggest to us the
things around the corner that we didn't see. That's where
the AI came in. That's really the genius of this.
Once it's all hard coded down, the AI does take
sort of a backseat to the code because once you
(26:08):
have to go fast, once you need to be efficient.
Speaker 4 (26:11):
You know.
Speaker 5 (26:12):
That's the way that you do it is you run
a whole bunch of traditional code and then you run
it through an interpretation model to be able to give
you natural language at the end. And that's super efficient
in AI. But it's an understanding of how to deploy
both of those things in concert and have the right
kind of people.
Speaker 3 (26:27):
So walk me through here, IBM, what are they doing.
They're taking the video feed, they're taking the data feed
the data feed.
Speaker 5 (26:35):
Correct, it's instead of trying to have them extract everything
out of the video feed, We've already done a lot
of that stuff and we're doing it at speed. So
we have my data feeds, and then we also have
any augmented information that we may be getting from external
AI computer vision systems, and that's coming in as the
source data to IBM. So now they're getting they're getting
(26:55):
a data feed, and they're getting it at speed. Their
job is to bust open that data feed into all
of the various questions that somebody might ask and think
about the interrelationships between data. So sometimes it's as simple
as this person is on pace to set the largest
number of takedown attempts we've seen the last twelve months
(27:16):
in this division. It's like a really nice talking point,
relatively simple all the way too. Here are two comparative
metrics for these two fighters, one of which is this
is his strength and this is his strength, and here's
how they're matching up right now and everything in between.
And to do that at speed.
Speaker 3 (27:32):
Yeah, so they're taking two things. They're taking the data
stream from your scores and then also so you have
these vision cameras.
Speaker 5 (27:43):
Yeah, it's a computer vision AI STAT system that we're
using to augment our STAT system.
Speaker 3 (27:48):
And how does that work?
Speaker 5 (27:50):
So the way that works is we've finally found somebody
who could do two things for us, give us accurate counts,
and be able to do so without us attaching a
whole bunch of cameras to the octagon, right, So they
can do it directly off of my handhelds, and they're
able to do things like give us combo percentage. They
can do punch and CounterPunch because they can assess that,
(28:14):
they could.
Speaker 4 (28:14):
Talk about style.
Speaker 5 (28:15):
That's a cross, that's a round house, that's right, those
kinds of things, and all of that is additive. Plus
by the way, they brought back all the motion stuff
because now my AI computer vision can actually do motion
for real, and so they brought all that back in
as well into the.
Speaker 3 (28:30):
Way I can now do just because the tech is better.
Speaker 4 (28:33):
Text a lot better.
Speaker 5 (28:34):
The ability to just know there's blue tape on the
blue fighter's wrists and red tape on the red fighter's wrist,
and we've gotten to the point now where scaltill tracking
and computer vision is able to identify people by that
and also take additional notes that dude's in green shorts
and that dude's in yellow shorts, right, and it'll do
those kinds of things to just figure out who's who.
And the hardest thing for a computer vision system to
(28:56):
do as it does motion is when we become the
eight legged B and we come apart. It can know
that we're purple, right, we're red and blue at the
same time, but when we come apart, it has to
rapidly understand who's red and who's blue. Again, that's where
a lot of these motion systems had a lot of difficulty.
Refs in black pretty easy to figure out, like somebody's
dressed in black.
Speaker 4 (29:16):
Head to.
Speaker 3 (29:17):
You've got these data streams, and presumably there is some
overlap between them, but that's fine. You're just feeding as
much data as you can from these two different sources
into the IBM black box, and the black box is
generating stories for us, ideas, observations, insights.
Speaker 5 (29:40):
I can give you a little more detail on how
it happens. I think that the beauty of unpacking how
AI works is there are moments of magic and moments
of drudgery, and they have to work perfectly together.
Speaker 4 (29:50):
Right AI.
Speaker 5 (29:51):
The data comes in to IBM, and it has a
storage system called Iceberg, and it runs a classic data
process called ETL. It's extract transform load. We care about
our data at the fight level or the round level.
IBM is trying to tell us things about our fighters,
so it is consolidating all of its information in these
big fighter tables that it can then sick the AI on,
(30:15):
and then the data moves from this etl iceberg level
up a level. They actually, I think they do it
by metals, So you start at bronze and you move
all the way up to gold and you move up
a level. So now your data is mezzanined basically for
the for the actual AI system to be able to
draw on it and efficiently process this data into insights,
(30:36):
and then it moves up into insight delivery, where we
have an interface that allows us to not just look
at insights. But then I have a human factor's problem.
My human needs to see the insights and he can't
see or she can't see all of them. Right, that's
way too many. So you have to have a scoring
system that says this insight is more relevant than this insight,
(30:56):
and surface only those so that a human Actually, this
was true of Watson a long time ago, right when
it did medical diagnostics. It couldn't give you the answer.
It could give you seven answers, and a doctor would
look through them and say it, got it, got it.
That's silly, that's silly. Hadn't thought of that one? And
that was the value right here. And we have a
similar thing right where we'll get a whole list of
(31:18):
them and you get to pick one of them and
be like go. And so that's how the data comes in.
And to everybody else that should be a black box.
But I'd prefer it not be a black box to us.
Speaker 3 (31:28):
In the course it is my possibility of question, in
the course of a fight, how many insights are being generated?
Speaker 4 (31:36):
Yeah, that's an excellent question.
Speaker 5 (31:38):
So in an active let's say we'll pick what I
would consider to be the Cadillac of fights. Right, So
it's five rounds, it's a championship fight. So you have
two fighters with long history, good records in that fight.
I mean it could be it could be a thousand,
a thousand, because because every permutation is possible. Yeah, right,
(32:01):
So the system is generating just an enormous amount, and
the real the intelligence is in filtering it out so
that my humans don't see a thousand, My humans see
fifteen fifteen. Yeah, because remember the moment that in a fight,
there's not a lot of chances, right, I'm not going
to spit out all fifteen onto the screen. In traditional statistics,
(32:22):
I've got two stats around. Maybe we don't have any
stats at the first half of the first round. If
something as amazing as happening, my job is to move
out of the way and just let that sit on
the screen, And so my insights are there to be
the most valuable thing I can put on screen at
that moment. And that's going to happen in a fight
twice and over the course of the night ten times.
(32:44):
But when it happens, everybody should have been talking about
this fight like this, and now they should be talking
about this fight like that.
Speaker 3 (32:52):
Give me an example of the kind of insight you
get that you probably would never have gotten in the
kind of previous sure universe.
Speaker 5 (33:01):
Sure, I think compound insights are the most complicated right
where it's we used to get basic, basic, but difficult
to answer questions when was the last time someone want
to fight after being down one hundred strikes? Like that's
a hard thing to throw into a sequel database at
the Latin a moment's notice and get that answer. But
you can do that kind of thing with INSIGHT's engine.
(33:22):
Right was like, You're like, oh, it is looking for
it's one of its pipelines. It's looking for those kinds
of disconnects between the data and the reality.
Speaker 4 (33:30):
This is the.
Speaker 5 (33:32):
Largest differential striking differential between two fighters, you know, in
a middleweight title fight since and here's this other iconic
fight that everybody remembers. Right, It's those kinds of things
that you might in the back of your head think
to yourself like, huh, this feels like I don't think
I've seen this in a while.
Speaker 4 (33:50):
But you can't.
Speaker 5 (33:51):
You can't give voice to it. And in a live fight,
there's very little time. So what will happen is two fighters,
Let's say it's a striking statistic. Two fighters have not
had this much of a striking differential in a fight
since X point. It is currently three minutes into the
round of round three, let's say, and the commentators are talking,
(34:12):
we're watching the action, everything's happening. You get this sense
in your head, I need to get in the next
two minutes. The last thirty seconds are already we're going
out to commercial like we're not interrupting that the fight
could end at any moment, So there's time pressure I've
got to hit a promo at some point in the
middle of this thing, So you see how my time
is getting shorter and shorter. To be able to deliver this,
(34:33):
I've got to have my producer be able to communicate it.
To the producer, it's got to communicate it to commentators,
who's got to be able to get it out of
a system into a graphic and then sold in to
be able to put on screen.
Speaker 4 (34:43):
All of that has to happen in call it between thirty.
Speaker 5 (34:47):
I said to you, like, I have three minutes, so
I have two minutes left in my round, probably only
have about forty seconds window, and I'm going to lose
it starting the moment I think of it until the
moment it hits screen. So I've got to have about
a fifteen second turnaround. And so it's not you don't
have to ask a very complex question for you to
exceed the fifteen second turnaround unless it's at your fingertips.
(35:08):
And that's what insights engine is for. It's it's to
kind of come in and be like, I know you
have some cool ideas, but we're never going to be
able to get him into fight time unless something is
pushing not pulling.
Speaker 3 (35:19):
You need to have buy in from the commentators.
Speaker 4 (35:22):
Yes, we do so.
Speaker 5 (35:24):
First of all, being a commentator is a very sophisticated
undertaking almost anything you see. And it's one of those
things that you watch happen and you say, well, that
doesn't look that difficult. But a commentator has an IFB
a little ear piece in and I've watched them do
this and I can't wrap my head around doing it,
which is you must be looking at the camera and
presenting information in coherent pros while the producer is talking
(35:45):
in your ear, and then when you stop talking, he
starts talking. No, no, no, it's talking in your ear while
you're talking. And you've got to be able to process
that information and two sentences hence make a part of
your delivery. And that information processing capability is by in
large sophisticated. Now, people are people. Some people are more
pro stat some people are more you know, anti static.
(36:08):
It doesn't really matter. You just have to know who
that is. But they have a relationship of trust with
their producer, and if the producer says I want to
go here.
Speaker 4 (36:19):
They can push back.
Speaker 5 (36:20):
But those two people work together on the regular producer's
going to sell you the things he thinks you're going
to buy, right, or at least the things he thinks.
This is as far as I can push it, and
you'll really go there because he wants you to sound
authentic and he certainly doesn't want you to be fighting
with him on air, right, So that very human process
is taking place. And by and large, one of the
(36:40):
reasons Insights Engine produces human readable stories is because I
would have pushed back if somebody said, IBM Insights Engine
says that so and so is fifty seven point two
four six percent likely to win the fight, Like okay,
and that doesn't feel authentic. But so like we've noticed
(37:01):
that he's advancing and he's a counterpuncher. This is off
and so now hopefully the commentator is going like, wow,
the movement in this fight is different than we would
expect to see, and let me give you some things
to bolster that that point. Or and people have done this,
We have given them an insight and they're like, oh, yeah,
you're right, Like that's what's weird yeah about this fight?
Speaker 3 (37:24):
Yeah, it's fascinating because genuine engagement with the insights. He's
actually from the viewers standpoint, the most interesting thing, the
idea that they would be there'll be some tension between
what we're seeing and what's actually happening. That is one
of the most interesting things in sport, right Oh, I thought,
(37:44):
I thought, you know, Steph Curry had a great game,
and then I look after at the stat line afterwards
and I'm like, or the opposite is even better. He
looked terrible out there. I look at the statline, He's like,
oh my god. He was like, I find my shot
seventy percent from the field.
Speaker 5 (37:59):
I feel like I do that more often than not,
where you're like, that looks terrible. So a couple of
things that are true in fighting that are I think
true elsewhere is if people have a favorite, they tend
to watch their guy, and so their guy always, unless
he looks terrible, he looks great because you're not watching
the other guy. You're just watching your guy, and that
stats help bridge that gap a lot. Our commentators in
(38:20):
general don't fall into that trap, and so when people
fight with the commentators. When when fans fight with the commentators,
they're watching one guy, They're not watching both guys. I
will watch fights and I will say, you know, I'm
not watching I'm not seeing the fight you're seeing. Some
of that is because a lot of our commentators are practitioners.
They're seeing something I'm not seeing and they but it
is then their job to explain to me what I'm
not seeing, and that's fine. I think that The other
(38:42):
place that I would want to take this, and where
insights I think are very useful, is our fans watching
a lot of contexts a lot and how many times
have you walked by a game?
Speaker 2 (38:53):
Right?
Speaker 5 (38:53):
The classic is I'm at a sports bar and maybe
the audios on, but maybe the audio is not. Maybe
it doesn't matter because it's loud. I want to be
able to provide an experience for that person that is
meaningful and potentially more meaningful. So, yes, my insights are
going to interact with my commentators. But if I can't
hear the commentators, how nice to be able to put
a storyline, not just a number, but a storyline directly
(39:14):
on screen. Right, we'll have this with milestone so and
so has exceeded their best ever whatever, and it's just
a moment where you're watching it like that's cool, and
you'll go back to watching.
Speaker 4 (39:22):
And that's really that's what we're going for.
Speaker 3 (39:25):
Are we fundamentally changing the relationship between the fan and
the sport.
Speaker 4 (39:29):
Interesting. I I didn't set.
Speaker 5 (39:32):
Out to have insights engine fundamentally change the relationship of
the fan and the sport. I wanted. I wanted something
to fit like a glove. Right if if you were
sitting next to someone who had an encyclopedic understanding of
the sport and they were in and they were fun, right,
(39:52):
that was a big part of it. What are the
kinds of things they could tell you where you're like, oh, cool,
and it's more fun to watch because of that and
not I think where a lot of the push was
in adding tech to the sport, which is we're gonna
make it nerdier like that was the thing I don't
want to do. I'm interested in leaning in to what
(40:15):
makes this great and letting you see writ in the
classic the stats to make the invisible visible, letting you
see those things but in a narrative arc so that
you can contextualize them. You can say something more intelligent
about sport, but like it. I wasn't here to make
you feel like I changed the sport. I was here
(40:35):
to make you feel like you were spoken to more
crisply about it. You were able to speak more crisply
about it, and the fight just looked a little shinier,
a little brighter because of this kind of thing. And
like I said, when this tech does its best work,
it just disappears.
Speaker 3 (40:55):
Hearing you describe it, it strikes me that what you're
doing is you're moving people up a level.
Speaker 5 (41:01):
You're right, we are bringing it to a place where
you feel like you can you could even have an
opinion because you understand enough of what's going on. You
are one hundred percent right. We're moving everybody right right
up the scale on a daily basis. I want to
go back to INSIGHT's engine is not here to feel technical,
and that's the genius of it. It's simplicity. It's narrative
(41:23):
is the thing that allows you to bring people forward
because you're not using jargon, because you're not just into
the numbers, right, That's really that's really the key here.
Speaker 3 (41:32):
When you look back at your experience with fight data,
are there a few categories that are essential to winning?
Speaker 5 (41:40):
I think the easiest way to answer that is the
entire statistical system that we built is based on only
one question.
Speaker 4 (41:49):
We don't track style.
Speaker 5 (41:53):
For example, I don't track whether somebody hit you with
a cross or a jab. Even more ridiculous, in the
official statistics, we don't track whether we hit you with
an arm or a leg. And that's because the entire
statistical system is built on this question what moved you
closer to winning the fight? And it turns out that
(42:14):
what moves you closer to winning a fight is where
you take damage, right, and how much damage you take.
So if I hit you in the head, arm, leg
doesn't really matter, style doesn't really matter, it's did it land?
So the whole statistical system is built on that question
of how much of each of these things did you do?
These things which we have directly correlated to victory, And
(42:37):
with live statistics and the augments, we can do lefts
and rights and things like that people want to see.
But that's the fundamental question. So for the question is
what's the most important thing you could do?
Speaker 4 (42:49):
Land strikes?
Speaker 5 (42:50):
Land significant strikes to the head that's going to end
most fights. Can you end a fight with significant strikes
to the body that massively outpace your opponent?
Speaker 4 (42:58):
You can?
Speaker 5 (42:58):
There at a second level, down can And then there
are things that are a little harder to talk about
that way, if you have more ground control, that's putting
you closer to completing a submission. So that again is
the kind of thing. And obviously once we get to
the number of submission attempts you attempt, are going to
make it more likely that one of those will be successful.
(43:19):
But it is all built from this basic question of
all of our stats, does it get you closer to
winning the fight?
Speaker 2 (43:26):
Yeah?
Speaker 3 (43:27):
One last question. I know you've thought about this a lot,
which is next. What's like if I, IF I, if
I invite you back. We have this conversation five years soon. Now,
what is the fun wrinkle that you're working on.
Speaker 4 (43:40):
We have a couple of things that are in the works.
Some of them are very sideways to this, but there so.
Speaker 5 (43:49):
One of them, which we're prototyping is the ability to
bring additional voices into the mix seamlessly. So I'll give
you a perfect example. If the coaches who are on
the side and they're yelling in whatever language they are yelling,
they are attempting to influence the fight, and it is
and we do this occasionally. We'll cut to the coaches
(44:11):
camp and we'll listen to them for a moment, but
they're doing it constantly, wouldn't it be interesting to understand
what they're trying to do and what it means. So,
for example, if I'm saying you're doing great, but you're
not doing great by being encouraging. If I'm saying you
are doing great and you are doing great, what does
that mean? What is my tone of voice, what's my
level of stress? All of these kinds of things, so
(44:31):
that you could very subtly be able to distill that
information and bring it in and say, like, by the way,
if you want to know what.
Speaker 4 (44:40):
The coaches think, feels interesting? So that's like a really
nice one that's relatively close.
Speaker 3 (44:45):
Now I have a sense of the psychological context of
the coach and the athlete.
Speaker 5 (44:49):
Let's go further away, right, You said five years in
the future. I think five years in the future. I
have two beliefs. I don't believe people want to lean
forward experience, as much as everybody would love them to
want to lean forward experience. If you could watch a
Steph Curry performance and I could let you controlled the camera.
Speaker 3 (45:08):
No, I don't want to get OK.
Speaker 4 (45:09):
I don't believe that people do.
Speaker 5 (45:11):
Yeah, but that doesn't mean that those technologies don't have
a place. So people are talking about vogumetric capture or
GAUSSI and splatting, all of these kinds of things that
allow you to create three dimensional space and move through it.
Speaker 4 (45:22):
I am working on.
Speaker 5 (45:23):
I have a belief that one of the places I
can't put a camera imagine the two of us were fighting,
is right here, right in front of my face and
watching your face. And yet the explanation you want to
give of I hit Malcolm in the shoulder because he
had dropped his hand and it was open.
Speaker 4 (45:38):
Show me, make it available to me.
Speaker 5 (45:41):
Speed up that process fast enough, create the telestration tools
fast enough. And I think that in five years those
things are going to become rote and we will expect
impossible angles, all of these kinds of things to become
part of our world. We are going to have to
rethink what it means to watch to be a fan
of something. If you only watch a fifteen minute cutdown
(46:04):
of a NASCAR race, are you a fan or not
a fan?
Speaker 4 (46:07):
I don't know.
Speaker 5 (46:07):
Do you watch fifteen minute cutdown of every race? And
how do I service that person and how do I
engage with that person? If you do have this very
for you said earlier that people only watch a half
a show. For example, if you have a fragmented set
of attention, I can either fight it and rage against
the dying of the light, or I could lean into
it and try to service that person and make them
a real fan and bring them into the rest of
(46:28):
our ecosystem. And I think that that is going to
continue to happen. I think we're going to continue to
make an argument for live events, and the pull of
that one only needs to go. As I'm sure you've seen,
when you're in the room, there's nowhere you'd rather be,
and it is so interesting, even though it is so
much less good than the angles you see on television,
you can't help but look away. We're bought in on
(46:50):
that thesis. But the moment you step out of that room,
how do I give you the greatest experience possible?
Speaker 2 (46:56):
Yeah?
Speaker 3 (46:56):
Yeah, alone, Thank you very much.
Speaker 4 (47:00):
Thank you.
Speaker 3 (47:01):
You maybe want to become a UFC fan, which is
a statement I never thought I would ever say.
Speaker 4 (47:05):
I'll tell you what, Come watch one with us, Come
watch one with me?
Speaker 5 (47:08):
Yeah, I bet you walk away and you're like, I'm
not sure I watching every week, But holy moly, is
this amazing?
Speaker 3 (47:15):
Smart talks with IBM is produced by Matt Romano, Amy Gaines, McQuaid,
Trina Menino and Jake Harper. Were edited by Lacy Roberts.
Engineering by Nina Bird Lawrence, mastering by Sarah Buguire, music
by Gramoscope, Strategy by Cassidy Meyer and Sophia Derlin. Smart
Talks with IBM is a production of Pushkin Industries and
(47:36):
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 Glappo. This is a paid advertisement
from IBM. The conversations on this podcast don't necessarily represent
IBM's positions, strategies, or opinions
Speaker 5 (48:02):
And STI
Hey everyone, it's Robert and Joe here. Today we've got
something a little bit different to share with you. It's
a new season of the Smart Talks with IBM podcast series.
Speaker 2 (00:09):
This season on Smart Talks with IBM, Malcolm Gladwell is back,
and this time he's taking the show on the road.
Malcolm is stepping outside the studio to explore how IBM
clients are using artificial intelligence to solve real world challenges
and transform the way they do business.
Speaker 1 (00:25):
From accelerating scientific breakthroughs to reimagining education. It's a fresh
look at innovation in action, where big ideas meet cutting
edge solutions.
Speaker 2 (00:34):
You'll hear from industry leaders, creative thinkers, and of course
Malcolm Gladwell himself as he guides you through each story.
Speaker 1 (00:41):
New episodes of Smart Talks with IBM drop every month
on the iHeartRadio app, Apple Podcasts, or wherever you get
your podcasts. Learn more at IBM dot com slash smart Talks.
This is a paid advertisement from IBM.
Speaker 3 (00:57):
I'm Malcolm Gladwell and you're listening to Smart Talk with IBM.
Most of what happens in a UFC fight is too
fast to see. A fighter drops their shoulder for a
split second. Did you catch it? A shift in position
that looks insignificant but changes everything? Were you watching alone?
(01:17):
Cohen is the head of R and D for UFC.
His job is to help people see those moments, not
by slowing things down, but by knowing what to point
to after it happens. By the time you realize something mattered,
his data systems have already figured out why it's taken
fifteen years to get here, first with paper scorecards and
a TVO, now in partnership with IBM, and along the way,
(01:42):
a loan's learned something that applies far beyond fighting. The
best technology is the kind you don't.
Speaker 4 (01:49):
Notice at all.
Speaker 3 (01:50):
It just helps you see. I thought you were going
to be like tattoos muscle shirt. I thought you were
going to like I thought you were going to represent
the brand in that respect that you yourself would be.
It would be a kind of, you know, mixed martial
arts type. You were not, in fact a mixed martial
(02:11):
arts type.
Speaker 5 (02:12):
I did a little taekwondo in my past. I am
I am not in the way that you put that,
not a mixed martial arts type. But I think if
you if you come through the building in Vegas. If
you come through the building when we do a show,
you're going to see a lot of the mixed martial
arts type. It even surprised me. I came out of
the tech world, the young tech world in the two thousands,
(02:34):
and everybody was talking about, you know, we have to
have a mix of viewpoints and a mix of you know,
people from all walks of life, and all of these
other things that evolved into into something else. But yeah,
that didn't happen to me until I went to work
for UFC, which is like a weird way to get there.
Speaker 3 (02:49):
Were you in a tech world before? What were you doing?
Speaker 5 (02:51):
So when I left school, I went to a startup
that today we would call a big data company, and
it was there at a moment where everybody was doing
relational databases and relational databases from micro Strategy and from
Cognos and from whoever. So we did that two thousand
and one hits after I graduate nine to eleven and
(03:12):
the dot com bust and all that kind of stuff,
and we all looked at each other and we said,
no one, no one of these institutions that needs this
kind of information is going to take a risk on
a small company right now, they're going to retrench.
Speaker 4 (03:23):
And I went to law school.
Speaker 3 (03:26):
Oh, I see, you started tech. You briefly have a
foot in the twenty first century, and then you decide, no,
I'm going to go get a law degree.
Speaker 4 (03:34):
I did.
Speaker 5 (03:35):
People said, you feel like somebody who would benefit from this,
and I wanted to want it. And the first attorney
I worked for out of law school, he looked at
me and he goes, you need to go be in business,
like you're not an attorney.
Speaker 3 (03:50):
Yeah, so you're you're a failed lawyer. They kick you out.
Where do you go next?
Speaker 4 (03:56):
So that's what happened.
Speaker 5 (03:57):
So in two thousand and eight, there were a bunch
of lawyers who were doing just fine, but the bottom
has fallen out of the legal market. I was helping
a friend off the side of my desk who had
come to me with a banker's box of paper and said,
I have been watching The Ultimate Fighter, the reality show
where they pick new entrance to the UFC, and I
had been watching. He was a sports writer before, and
(04:18):
he very much. This gentleman's name is Romick an hour
romy comes to me and he says, there's no stats
for this stuff.
Speaker 4 (04:25):
I'm used to writing about baseball.
Speaker 5 (04:26):
So I did a full regression analysis after watching one
hundred hours of fight time, and now we're at closer
to two hundred hours of fight time. And I've been
scoring these fights, and the UFC's talent have been reading
my blog and they want me to do analysis for them,
and I can't be doing it on paper. And so
he came to a technologist and said, what do I do?
And we talked about double king the data in Indonesia
(04:47):
and building a database and APIs. A year later, we
were making small salaries and we had gotten this thing
up off the ground and going, and the UFC was
starting to use our statistics, and we had turned it
into a real data product. You know, we were able
to score electronically at that point. And the rest is
at this point seventeen or eighteen years of history.
Speaker 3 (05:06):
So wait, back up, this is really interesting. Pretend I
know nothing about UFC. Okay, So Romi comes to you.
And Romy's issue is what that the way in which
these matches are scored is too subjective.
Speaker 5 (05:20):
The way that these matches are scored is inscrutable to
the average person. So his analogy, and it's the one
that he experienced is when you write a summary of
last night's baseball game, right, what do you do?
Speaker 4 (05:33):
You say, here's my thesis statement.
Speaker 5 (05:36):
So and so had a great outing, and middle relief
collapsed or whatever it is, and last night at seven
pm at this stadium, the following happened. Here was the
final score. And then this middle paragraph is, you know,
middle relief had this as a cra and so on
and so forth, and you'd run an analysis and then
you talk about, you know, so and so has been
performing well and he had this outing and that outing
and blah blah blah blah.
Speaker 4 (05:55):
This is part of a trend.
Speaker 3 (05:56):
You tell the story of the game and the context
of a core of statistical.
Speaker 5 (06:01):
Knowledge exactly right. And this is at least how he wrote.
And you get to that paragraph in an MMA story
and it's non existent. It's so and so is a
strong striker. So and so is coming off of two losses,
so and so is on a three fight win streak.
And that is the totality of what's currently available. And
Romy's approach is we can count everything, but everything's not important.
(06:25):
And you can't count everything practically because by the time
he gets to the end of this first iteration, we
have sixty seven data points per fighter per round.
Speaker 4 (06:33):
So it's a ton of stuff.
Speaker 3 (06:35):
At this point, you're collecting the data.
Speaker 5 (06:37):
How just visually, he has a piece of paper and
he is on a TVO. Remember TV's. We had TV's
until long after they were dead because we needed them.
And he is playing and pausing and rewinding to be able.
Speaker 3 (06:48):
To He's doing it the way people in the olders
in baseball, remember they would score. Sure, they would take
the piece of paper and they would score the game
as they were watching. It's flowing to matches.
Speaker 5 (06:57):
His history is I go to baseball games with dad.
Dad has a scorecard, and you, as a kid, are
both drawn to it and averse to it because you're
like dad, you're missing the game, and at some point
you find yourself marking down the scorecard.
Speaker 4 (07:09):
And he brings a lot of that to this.
Speaker 3 (07:12):
So you say in his first iteration he had seventy
two data points, say that again, sixty seven sixty seven
data points per fighter fighter per round per round.
Speaker 4 (07:23):
Yeah, so that's.
Speaker 5 (07:24):
Consistently there or this as an average of Well, so
at any points on the sheet, there are sixty seven
different things that we are tracking. So there may be
more head strikes landed, powerhead strikes landed, and there may
be some other head strikes landed, but there's probably not
necessary tight submission or a camorra or something like that.
But these are different kinds of submission types that we
(07:45):
would track, and so all of them are available on
the sheet so that you can just tick those off
and move on. Right, So those are the sixty seven
independent boxes on the sheet that we could mark something
down on.
Speaker 3 (07:55):
Give me examples of things that non obvious things that
you would learn if you did a formal statistical analysis
of a match, like as a viewer or as a fan.
How is this enhancing his experience of what he's watching.
Speaker 5 (08:08):
A couple of things are happening inside of an MMA
match that are worthy of note to the average fan.
It is scored per round. And one of the problems
that you have when you score per round is that
people don't think per round right. They don't get to
the end of round one and say round one is over.
I will make a decision about round one, let us
now go to They don't do that. They look at
(08:29):
the totality of the match. The shorthand I used for
this for a long time is you make the invisible
visible to people like.
Speaker 4 (08:36):
What exactly did I see?
Speaker 5 (08:37):
The other thing that the last thing that the numbers
do for us is they tend to combat recency because
you just forget what happened in round one or it
just doesn't leave as strong an impression. And one of
the and of course fighters fight to that what do
you do right at.
Speaker 4 (08:51):
The end of the round?
Speaker 5 (08:52):
You take a dude and you take him down because
you were going to finish the fight now because you
wanted to leave in the impression and the impression in
the mind of the judges like that do you controlled
that round? And so you were trying to score these
big shots at the end of a round, and the
numbers allow us to battle some of that for our
fans to say, like, how well did he actually do?
Speaker 4 (09:10):
What did she actually do in this thing?
Speaker 5 (09:12):
So that's one of the big learnings is you're able
to go back in time and not have to watch
the video. You just get a spot to be like, oh, yeah,
there are two takedowns in that first round.
Speaker 3 (09:21):
And so you're allowing people to construct a much more
complete and accurate narrative of the of the match.
Speaker 5 (09:28):
I think so yeah, And I think for new fans
there's a different calculus because new fans don't know how
to watch the sport. And when you it's I joke
that when we all watch the Olympics, like, I don't
know anything about synchronized swimming and I shouldn't pretend to,
but the Olympic broadcast allows me to pretend to, right,
(09:49):
And that's a little bit of what's happening here is
that they can look at this and say, oh, I
get it right, Like I'm watching all this action, and
then we condense that down to this is the number
of like kicks this person landed, and they're like, oh,
I did see Okay, Now I know to focus on that.
This is part of the storyline and it is a
signpost and that's a big deal.
Speaker 3 (10:08):
So in the beginning, you're just a contractor with UFC.
Speaker 4 (10:11):
We are a contractor entity.
Speaker 2 (10:13):
Yeah.
Speaker 5 (10:13):
For the first seven years of our existence, we are
independent and are the official data feed of the UFC.
Speaker 3 (10:19):
And and at a certain point UFC says, come and
join the.
Speaker 5 (10:25):
Ari emmanual at wm IMG at the time buys UFC
and he says, I want to sell the data.
Speaker 4 (10:31):
Where's the data?
Speaker 5 (10:32):
And they said, well, these two nice kids in the
Georgetown waterfront they have the data, and he goes, what
do you mean they have the data? Like, it's our data,
and that started an acquisition. Conver We were a fold
into that larger acquisition.
Speaker 3 (10:43):
Going back to the fights, the data, how is it?
How is the scoring working at this point?
Speaker 4 (10:48):
So the tvo I brought up earlier, you're able to
watch it with slow moo and rewind and we have
at the time tablet or a touch screen, and we
have taken our piece of paper and we have split
it in twain and you're able to mark what you
see as you see it, save around you score.
Speaker 3 (11:03):
You've got trained scores, yes, yeah.
Speaker 5 (11:06):
They are some of my favorite people. We have had
trained scorers in our group that go back thirteen years
with us, folks that we plucked out of the ether. Right,
you put something online looking for people who are interested
in learning this stuff, and then you have to whittle
out the people who can learn how to do it
and then do it quickly. The first time you score
something like this and try to make sense of the
scoring page, it's going to take you fifteen minutes to do.
(11:28):
A five minute round might take you more. And that
means that at the end of the fight, you're probably
thirty five minutes late. And so you have to do
this for six or seven months on a regular basis,
paying you make sure that you know you're fairly compensated
to get you to the point where you're able to
make decisions rapidly. It just comes as second nature to you.
And this is the dirty little secret of UFC. But
(11:49):
we joke, we've been trying to put ourselves out of
that business for at this point eleven or twelve years
and we aren't close yet.
Speaker 3 (11:57):
Put yourself out of the business of having to rely
eye on a human score, a human score.
Speaker 5 (12:02):
Yeah, and we said that joshingly. But there's a sense
of which there's a sense in which at some point
you understand that compute ought to catch up with you, right,
And we said we should be out ahead of this
and sort of the Netflix model, Right, if DVDs are
going to be a problem, you shouldigure out what's coming next,
and you should do that also and disrupt yourself. And
(12:24):
you know, we wanted initially we have used it as
additive data, so we wanted to do motion tracking. So
eleven twelve years ago we bought a motion tracking software
and it couldn't make sense of any of what it
was seeing inside the octagon, like it really couldn't understand.
And this wasn't even striking. This is just like red
is here, blue is here, and the rough is here.
And so we taught a human system how to do it.
(12:44):
But we keep going back to the to the machine well,
hoping it will get better. And today, in fact we
are we are closer than ever, but nowhere near close
to overtaking us as scores.
Speaker 4 (12:55):
It's weird.
Speaker 5 (12:56):
I have been playing, as I said, with my motion
tracking computer vision experiments. We're twelve years ago. Ten years
ago I was hanging cameras to attempt to do a
skeletal tracking to see what that could give us, and
it didn't work. You know, we have been on a
ten year journey to discover what it can do and
being fostering of it. Right, That's what R and D
(13:20):
is supposed to say when something fails, to say, well
is there something of this that I can retain? Does
this add some value enough that it really makes sense
to just continue to invest in it some so if
it can ever make good on its promises, we'll get
to see exponentially.
Speaker 3 (13:36):
What striving you here is what you want to get
your data quicker? Or do you want more data? Do
you want qualitatively different data?
Speaker 2 (13:43):
What is it?
Speaker 3 (13:44):
What's what's what's in the back of your head?
Speaker 5 (13:46):
So man, so many motivations are pushing this for us.
One motivation is faster data. So imagine the following very simple.
If I see a significant strike landed in the middle
and so well, let's say the first person to one
hundred significant strikes landed in this fight, that is potentially
betting data. Somebody could bet who could get to that first.
(14:07):
Right now, I can only offer that data unofficially because
my humans need to wait for my official data to
come in. If computer vision could really get that right,
then I could stand behind that number and say that
is betting ready, and you could resolve that bet at
the moment it happens. And so you open up all
of these markets for one like that. That's a big
(14:28):
motivator for this kind of stuff. The second is I
am When I'm adding these AI technologies, I'm often looking
at them and saying, like, what else can I do
with this? What else is it telling me about the
fight that I'm not already getting motion was a big
one of them. Right, where are people in the octagon?
What I mentioned earlier that one of the one of
(14:49):
the criteria for judging a fight is control of the
octagon space. Well, okay, everything I was tracking with my
scores before doesn't talk about that.
Speaker 4 (14:56):
Right.
Speaker 5 (14:56):
If I'm hitting you more and you're you know, defending
poorly or whatever it is, maybe that's control. But what
if you're a counterpuncher, right, famous fighters who are counterpunchers.
I draw you in and then I hit you. Does
that mean I'm seating control to be able to take
back control?
Speaker 4 (15:10):
What does that mean?
Speaker 5 (15:11):
And so we didn't have any any numbers on where
people are. That's an immediate use of AI that is
additive to what I am doing. And all of this
is always in the service of storyline. Right, what is
not being captured in the fight? And what should the
commentators be talking about? And how can I support what
they're talking about? How can I give them something that
(15:32):
makes them think, Oh, actually, the thing I want to
be talking about here is this, Right, that's ultimately the
goal the goal here is I mean, let's go back
to the first thing you said. You said, I don't
look like the kind of person who might be an
MMA fan. There is a point at which if I
throw up a number on the screen and it's like,
this person is twenty seven point two four, and people
(15:53):
are like nerd, like, what are you doing? And there
is a space for that in other sports, but sometimes
we're doing it just to seem to technical. I think
if you're doing the tech right, you should forget about
the tech. You should forget about the fact that there's
AI behind that. You should forget about all of this.
The thing that hits the screen is so and so
has never lost a fight if they have landed four takedowns.
(16:17):
We're on number three. Right now, we know what we're watching. Yeah,
right now you have a binary, simple thing to look at.
So and so has a takedown accuracy of ninety four percent.
So and so has a takedown defense of seventy five percent.
Let's see how they match up against their classic averages.
And now you're getting into some more tech and number
you're like, this guy is below his average and that
(16:38):
guy's above his average. Okay, now we have a way
of measuring very quickly who's winning and who's losing. Across
at least this part of the fight, and so the
goal is to get to storyline as fast as possible
in human understandable terms. Right, This is in some ways
the great moment of the LM as well. Right, Who
cares how many weights and how many parameters and how
(16:59):
many whatever? When I talk to it, it feels like
I'm talking to a human. That's the great unlock. The
technology suddenly disappears and the experience stays. And that's at
our level, at our level of sophistication, that's what we're doing.
Speaker 3 (17:14):
Yeah, I want to go back to make sure I
understand when you talk about control of the octagon of
the octagon conceptually, what is control the octagon mean?
Speaker 5 (17:26):
It is the last of the criteria in the judging rules,
and it should mean that in a fight one of
the things you're trying to do is assert dominance the
most basic level.
Speaker 4 (17:40):
It is left vague.
Speaker 5 (17:41):
Different commissions around the country will tell you slightly different
things about what it means. Some of them will boil
it down to if I hit you more, I control
the fight, but a lot of others of them will
say it is really there to be that sixth sense
feel of was I able to put you where I
wanted you to be when I want you to be there,
(18:02):
and in our statistics, one of the ways you can
talk about that is advancing or center control. If I
always own the center, you always have the wall at
your back, so I control the space.
Speaker 4 (18:15):
Right.
Speaker 5 (18:15):
There are ways of finding small analogus directional pointers to
tell you that. But when you talk about what a
judge is looking for, they're looking for that ephemeral sense
of you know, who's the big.
Speaker 3 (18:31):
Dog, and that is if you're strictly kind of scoring
the match, that's one thing you're not picking up because
you're too focused on position, who's striking whom that kind
of larger gestal you're talking about a gestalt of right, Sure, yeah.
Speaker 5 (18:47):
Somehow the Novata State Athletic Commission to get to criteria
five and go gestalt.
Speaker 4 (18:52):
That's what we're looking for.
Speaker 5 (18:53):
We're trying to deal as a as a as a
matter of course, we want to bring people into our arena.
Have the six it's be devoid of Weltschmertz and focus
on the gestalt.
Speaker 4 (19:03):
And it just didn't. It didn't make it, That's what
I'm saying.
Speaker 3 (19:06):
So you've got your motivations are one I can enhance
the viewer experience in terms of story. Yep, I can.
I can facilitate things like betting on the on the match,
and I can aid the judges in getting a sense
of who the dominant party is.
Speaker 4 (19:25):
One and two.
Speaker 5 (19:25):
Yes, three, we actually scrub all of our all of
our video feeds into the arena, a scrubbed of our statistics.
I do not want the judges. Their job is to
follow the criteria set by their commission. So we're in
this weird spot where like my sport has, my fighters
are independent contractors. It's a regulated sport by the state
(19:47):
commission that we're dealing with, and my job is to
is to bring the event together. And as a result,
I don't want anyone pointing at us saying you said.
And so I decided we're like, look, you understand your criteria,
you're fully trained, judge. You need to decide who won
this fight. Our statistics will tell the story our statistics
tell and by the way, we can have an occasionally
antagonistic relationship where we thought that was a poor decision, right.
Speaker 4 (20:11):
Yeah, that makes it interesting exactly. Yeah.
Speaker 3 (20:13):
So okay, let's go back to the AI. So you're
you start experimenting with this a while ago. Oh yeah,
and you're not you're not entirely happy with the with the results.
Is that a fair or you're Oh, you understand it's embryotic.
Speaker 4 (20:28):
Both, right?
Speaker 5 (20:29):
You? Why should I start down the project of making
this work if I don't believe it's going to work?
Speaker 4 (20:35):
Right, I try?
Speaker 5 (20:37):
If I'm going to bother dedicating the time and the
effort and potentially a lot of money. I wanted to work. Uh,
and I was disappointed in time and again, and I
have found things to bring along right, So early skeletal
tracking has become the basis for today.
Speaker 3 (20:50):
SAT tracking is defined.
Speaker 5 (20:53):
The term skeletal tracking is when you hang cameras. Nowadays
you are very quickly able to discern what is is
not a human inside of your space, and then you're
able to identify points on their body, nowadays more points
than we used to.
Speaker 4 (21:07):
It used to be like.
Speaker 5 (21:08):
Shoulders, head, torso, hips, knees, feet, right, and nowadays you
have two additional points on the feet so you can
see their orientation. Hands you can see the orientation, and
face you can see where I'm looking. Those are basic
skeletal models and you need that to be able to
understand from an AI perspective, who is striking and was
(21:30):
that a miss?
Speaker 4 (21:30):
Was that a hit?
Speaker 5 (21:31):
We can get into collision detection, which is very difficult
because skeletal tracking isn't it's not the outside of your arm,
it's the inside. And then beyond was there a collision,
we get into problems of intent. So intent is the
hardest thing actually to solve. There's a lot of times
where two guys are fighting and one guy's going like this,
he's range finding, just putting a hand out there to
see is you know, how far away are you and
(21:54):
sort of to bat you away? And that is not
a strike attempt. How do you teach the computer that
that's not a strike attempt? Because sometimes it looks like it,
sometimes it doesn't. And then same thing with kick to
the head. It makes contact with the outset of my arm,
which I brought up in our world, that's a blocked strike.
(22:15):
But teaching a computer what exactly that means and when
and how like when it's up here, when my arm
is up, that's a block. When my arm is down
and hits my shoulder, that's not. It's those nuances that
proved incredibly difficult for machines to be able to handle
for a very very long time. And the acceleration in
the last few years which has allowed us to onboard
(22:36):
this technology has solved so many of these problems. At
the same time, we no longer need fixed cameras. I
now do it off the broadcast cameras, which are on
people's shoulders and they shake and they rotate and whatever
doesn't matter. It can still figure out what it's looking at.
This is the octagon, These are the fighters. Here are
their bodies, that's the ref He doesn't matter all of
that stuff. It can now figure out. It can begin
(22:57):
to understand what real landed myst is, and it can
do so on much less perfect data than we needed
the first time. That acceleration has been incredible. If I
didn't know step one and two and three and four,
I'm not sure how ready I would have been for
where we are now.
Speaker 3 (23:12):
Yeah, So let's just dig into where we are now
a little bit. So you go. I'm interested in the
partnership with IBM and the kind of transition from this
period of experimentation to where you are now. So where
at the time you guys, you're aware of.
Speaker 4 (23:30):
The development of AI yep.
Speaker 3 (23:33):
And it's getting better and better and better and better
and better, and you clearly have an intuition that, oh,
this is this could potentially really open some opportunities for us.
Speaker 4 (23:43):
Yep.
Speaker 3 (23:44):
What's the point in time where you start to think, oh,
this could be real.
Speaker 5 (23:49):
Our relationship with IBM is born of a little bit
of suffering on our behalf, is the best way to
put it. We had a partner as part of the
larger business that really wanted to focus on AI with us,
and we said, we would really like to do an
insights engine. We think it's really additive. These storylines in
real time would change the way that we talk about
(24:10):
the sport in broadcast. And for two years we went
down that road and it crashed and burned. We go
into the reasons, but they didn't understand the sport. They
tried to brute force the problem. And if you try
to brute force this problem, it's going to kill you.
And because there are just so many permutations out there,
(24:32):
and IBM starts a conversation with us, and very quickly
as we engage, a couple of things emerge, and they're
not about the tech. They say to us, we think
we can do it with the tech. We say, we
have to believe you that you can do it with
the tech. We don't know, we're not experts in it.
They can bring people who understand sports analysis to the table,
(24:53):
so all of a sudden, when my phone call ends,
when somebody at IBM has a question, they can talk
to somebody better. Yet, within the first of weeks, I said,
it would really be helpful to have somebody who's an
MMA fan, because some of your questions are specific to
the sport and we could answer them all the time.
But I think that the velocity here goes up if
you can just say, hey, Brad, what's happening here? Can
(25:15):
you explain what is the culture, what's important, what's not important? Right,
because you can come up with a lot of ideas
and fans will be like, I don't care, and it
gets worse from there.
Speaker 4 (25:24):
So we quickly eliminated that. With IBM.
Speaker 5 (25:27):
They had people on the bench who understood just the
area and then the specifics of our sport, and they
were able to fill in some of the gaps for us,
and so we could move at pace. And it was
all about the people at the beginning, and obviously beyond that,
they had to make good on the arctech and actually
do this. We can use the AI. It's not so
much that the AI needs to run the final product.
(25:48):
That's not what we're talking about. It's can the AI
speed up the creation of the product? Can AI help
us expand its reach? Can AI suggest to us the
things around the corner that we didn't see. That's where
the AI came in. That's really the genius of this.
Once it's all hard coded down, the AI does take
sort of a backseat to the code because once you
(26:08):
have to go fast, once you need to be efficient.
Speaker 4 (26:11):
You know.
Speaker 5 (26:12):
That's the way that you do it is you run
a whole bunch of traditional code and then you run
it through an interpretation model to be able to give
you natural language at the end. And that's super efficient
in AI. But it's an understanding of how to deploy
both of those things in concert and have the right
kind of people.
Speaker 3 (26:27):
So walk me through here, IBM, what are they doing.
They're taking the video feed, they're taking the data feed
the data feed.
Speaker 5 (26:35):
Correct, it's instead of trying to have them extract everything
out of the video feed, We've already done a lot
of that stuff and we're doing it at speed. So
we have my data feeds, and then we also have
any augmented information that we may be getting from external
AI computer vision systems, and that's coming in as the
source data to IBM. So now they're getting they're getting
(26:55):
a data feed, and they're getting it at speed. Their
job is to bust open that data feed into all
of the various questions that somebody might ask and think
about the interrelationships between data. So sometimes it's as simple
as this person is on pace to set the largest
number of takedown attempts we've seen the last twelve months
(27:16):
in this division. It's like a really nice talking point,
relatively simple all the way too. Here are two comparative
metrics for these two fighters, one of which is this
is his strength and this is his strength, and here's
how they're matching up right now and everything in between.
And to do that at speed.
Speaker 3 (27:32):
Yeah, so they're taking two things. They're taking the data
stream from your scores and then also so you have
these vision cameras.
Speaker 5 (27:43):
Yeah, it's a computer vision AI STAT system that we're
using to augment our STAT system.
Speaker 3 (27:48):
And how does that work?
Speaker 5 (27:50):
So the way that works is we've finally found somebody
who could do two things for us, give us accurate counts,
and be able to do so without us attaching a
whole bunch of cameras to the octagon, right, So they
can do it directly off of my handhelds, and they're
able to do things like give us combo percentage. They
can do punch and CounterPunch because they can assess that,
(28:14):
they could.
Speaker 4 (28:14):
Talk about style.
Speaker 5 (28:15):
That's a cross, that's a round house, that's right, those
kinds of things, and all of that is additive. Plus
by the way, they brought back all the motion stuff
because now my AI computer vision can actually do motion
for real, and so they brought all that back in
as well into the.
Speaker 3 (28:30):
Way I can now do just because the tech is better.
Speaker 4 (28:33):
Text a lot better.
Speaker 5 (28:34):
The ability to just know there's blue tape on the
blue fighter's wrists and red tape on the red fighter's wrist,
and we've gotten to the point now where scaltill tracking
and computer vision is able to identify people by that
and also take additional notes that dude's in green shorts
and that dude's in yellow shorts, right, and it'll do
those kinds of things to just figure out who's who.
And the hardest thing for a computer vision system to
(28:56):
do as it does motion is when we become the
eight legged B and we come apart. It can know
that we're purple, right, we're red and blue at the
same time, but when we come apart, it has to
rapidly understand who's red and who's blue. Again, that's where
a lot of these motion systems had a lot of difficulty.
Refs in black pretty easy to figure out, like somebody's
dressed in black.
Speaker 4 (29:16):
Head to.
Speaker 3 (29:17):
You've got these data streams, and presumably there is some
overlap between them, but that's fine. You're just feeding as
much data as you can from these two different sources
into the IBM black box, and the black box is
generating stories for us, ideas, observations, insights.
Speaker 5 (29:40):
I can give you a little more detail on how
it happens. I think that the beauty of unpacking how
AI works is there are moments of magic and moments
of drudgery, and they have to work perfectly together.
Speaker 4 (29:50):
Right AI.
Speaker 5 (29:51):
The data comes in to IBM, and it has a
storage system called Iceberg, and it runs a classic data
process called ETL. It's extract transform load. We care about
our data at the fight level or the round level.
IBM is trying to tell us things about our fighters,
so it is consolidating all of its information in these
big fighter tables that it can then sick the AI on,
(30:15):
and then the data moves from this etl iceberg level
up a level. They actually, I think they do it
by metals, So you start at bronze and you move
all the way up to gold and you move up
a level. So now your data is mezzanined basically for
the for the actual AI system to be able to
draw on it and efficiently process this data into insights,
(30:36):
and then it moves up into insight delivery, where we
have an interface that allows us to not just look
at insights. But then I have a human factor's problem.
My human needs to see the insights and he can't
see or she can't see all of them. Right, that's
way too many. So you have to have a scoring
system that says this insight is more relevant than this insight,
(30:56):
and surface only those so that a human Actually, this
was true of Watson a long time ago, right when
it did medical diagnostics. It couldn't give you the answer.
It could give you seven answers, and a doctor would
look through them and say it, got it, got it.
That's silly, that's silly. Hadn't thought of that one? And
that was the value right here. And we have a
similar thing right where we'll get a whole list of
(31:18):
them and you get to pick one of them and
be like go. And so that's how the data comes in.
And to everybody else that should be a black box.
But I'd prefer it not be a black box to us.
Speaker 3 (31:28):
In the course it is my possibility of question, in
the course of a fight, how many insights are being generated?
Speaker 4 (31:36):
Yeah, that's an excellent question.
Speaker 5 (31:38):
So in an active let's say we'll pick what I
would consider to be the Cadillac of fights. Right, So
it's five rounds, it's a championship fight. So you have
two fighters with long history, good records in that fight.
I mean it could be it could be a thousand,
a thousand, because because every permutation is possible. Yeah, right,
(32:01):
So the system is generating just an enormous amount, and
the real the intelligence is in filtering it out so
that my humans don't see a thousand, My humans see
fifteen fifteen. Yeah, because remember the moment that in a fight,
there's not a lot of chances, right, I'm not going
to spit out all fifteen onto the screen. In traditional statistics,
(32:22):
I've got two stats around. Maybe we don't have any
stats at the first half of the first round. If
something as amazing as happening, my job is to move
out of the way and just let that sit on
the screen, And so my insights are there to be
the most valuable thing I can put on screen at
that moment. And that's going to happen in a fight
twice and over the course of the night ten times.
(32:44):
But when it happens, everybody should have been talking about
this fight like this, and now they should be talking
about this fight like that.
Speaker 3 (32:52):
Give me an example of the kind of insight you
get that you probably would never have gotten in the
kind of previous sure universe.
Speaker 5 (33:01):
Sure, I think compound insights are the most complicated right
where it's we used to get basic, basic, but difficult
to answer questions when was the last time someone want
to fight after being down one hundred strikes? Like that's
a hard thing to throw into a sequel database at
the Latin a moment's notice and get that answer. But
you can do that kind of thing with INSIGHT's engine.
(33:22):
Right was like, You're like, oh, it is looking for
it's one of its pipelines. It's looking for those kinds
of disconnects between the data and the reality.
Speaker 4 (33:30):
This is the.
Speaker 5 (33:32):
Largest differential striking differential between two fighters, you know, in
a middleweight title fight since and here's this other iconic
fight that everybody remembers. Right, It's those kinds of things
that you might in the back of your head think
to yourself like, huh, this feels like I don't think
I've seen this in a while.
Speaker 4 (33:50):
But you can't.
Speaker 5 (33:51):
You can't give voice to it. And in a live fight,
there's very little time. So what will happen is two fighters,
Let's say it's a striking statistic. Two fighters have not
had this much of a striking differential in a fight
since X point. It is currently three minutes into the
round of round three, let's say, and the commentators are talking,
(34:12):
we're watching the action, everything's happening. You get this sense
in your head, I need to get in the next
two minutes. The last thirty seconds are already we're going
out to commercial like we're not interrupting that the fight
could end at any moment, So there's time pressure I've
got to hit a promo at some point in the
middle of this thing, So you see how my time
is getting shorter and shorter. To be able to deliver this,
(34:33):
I've got to have my producer be able to communicate it.
To the producer, it's got to communicate it to commentators,
who's got to be able to get it out of
a system into a graphic and then sold in to
be able to put on screen.
Speaker 4 (34:43):
All of that has to happen in call it between thirty.
Speaker 5 (34:47):
I said to you, like, I have three minutes, so
I have two minutes left in my round, probably only
have about forty seconds window, and I'm going to lose
it starting the moment I think of it until the
moment it hits screen. So I've got to have about
a fifteen second turnaround. And so it's not you don't
have to ask a very complex question for you to
exceed the fifteen second turnaround unless it's at your fingertips.
(35:08):
And that's what insights engine is for. It's it's to
kind of come in and be like, I know you
have some cool ideas, but we're never going to be
able to get him into fight time unless something is
pushing not pulling.
Speaker 3 (35:19):
You need to have buy in from the commentators.
Speaker 4 (35:22):
Yes, we do so.
Speaker 5 (35:24):
First of all, being a commentator is a very sophisticated
undertaking almost anything you see. And it's one of those
things that you watch happen and you say, well, that
doesn't look that difficult. But a commentator has an IFB
a little ear piece in and I've watched them do
this and I can't wrap my head around doing it,
which is you must be looking at the camera and
presenting information in coherent pros while the producer is talking
(35:45):
in your ear, and then when you stop talking, he
starts talking. No, no, no, it's talking in your ear while
you're talking. And you've got to be able to process
that information and two sentences hence make a part of
your delivery. And that information processing capability is by in
large sophisticated. Now, people are people. Some people are more
pro stat some people are more you know, anti static.
(36:08):
It doesn't really matter. You just have to know who
that is. But they have a relationship of trust with
their producer, and if the producer says I want to
go here.
Speaker 4 (36:19):
They can push back.
Speaker 5 (36:20):
But those two people work together on the regular producer's
going to sell you the things he thinks you're going
to buy, right, or at least the things he thinks.
This is as far as I can push it, and
you'll really go there because he wants you to sound
authentic and he certainly doesn't want you to be fighting
with him on air, right, So that very human process
is taking place. And by and large, one of the
(36:40):
reasons Insights Engine produces human readable stories is because I
would have pushed back if somebody said, IBM Insights Engine
says that so and so is fifty seven point two
four six percent likely to win the fight, Like okay,
and that doesn't feel authentic. But so like we've noticed
(37:01):
that he's advancing and he's a counterpuncher. This is off
and so now hopefully the commentator is going like, wow,
the movement in this fight is different than we would
expect to see, and let me give you some things
to bolster that that point. Or and people have done this,
We have given them an insight and they're like, oh, yeah,
you're right, Like that's what's weird yeah about this fight?
Speaker 3 (37:24):
Yeah, it's fascinating because genuine engagement with the insights. He's
actually from the viewers standpoint, the most interesting thing, the
idea that they would be there'll be some tension between
what we're seeing and what's actually happening. That is one
of the most interesting things in sport, right Oh, I thought,
(37:44):
I thought, you know, Steph Curry had a great game,
and then I look after at the stat line afterwards
and I'm like, or the opposite is even better. He
looked terrible out there. I look at the statline, He's like,
oh my god. He was like, I find my shot
seventy percent from the field.
Speaker 5 (37:59):
I feel like I do that more often than not,
where you're like, that looks terrible. So a couple of
things that are true in fighting that are I think
true elsewhere is if people have a favorite, they tend
to watch their guy, and so their guy always, unless
he looks terrible, he looks great because you're not watching
the other guy. You're just watching your guy, and that
stats help bridge that gap a lot. Our commentators in
(38:20):
general don't fall into that trap, and so when people
fight with the commentators. When when fans fight with the commentators,
they're watching one guy, They're not watching both guys. I
will watch fights and I will say, you know, I'm
not watching I'm not seeing the fight you're seeing. Some
of that is because a lot of our commentators are practitioners.
They're seeing something I'm not seeing and they but it
is then their job to explain to me what I'm
not seeing, and that's fine. I think that The other
(38:42):
place that I would want to take this, and where
insights I think are very useful, is our fans watching
a lot of contexts a lot and how many times
have you walked by a game?
Speaker 2 (38:53):
Right?
Speaker 5 (38:53):
The classic is I'm at a sports bar and maybe
the audios on, but maybe the audio is not. Maybe
it doesn't matter because it's loud. I want to be
able to provide an experience for that person that is
meaningful and potentially more meaningful. So, yes, my insights are
going to interact with my commentators. But if I can't
hear the commentators, how nice to be able to put
a storyline, not just a number, but a storyline directly
(39:14):
on screen. Right, we'll have this with milestone so and
so has exceeded their best ever whatever, and it's just
a moment where you're watching it like that's cool, and
you'll go back to watching.
Speaker 4 (39:22):
And that's really that's what we're going for.
Speaker 3 (39:25):
Are we fundamentally changing the relationship between the fan and
the sport.
Speaker 4 (39:29):
Interesting. I I didn't set.
Speaker 5 (39:32):
Out to have insights engine fundamentally change the relationship of
the fan and the sport. I wanted. I wanted something
to fit like a glove. Right if if you were
sitting next to someone who had an encyclopedic understanding of
the sport and they were in and they were fun, right,
(39:52):
that was a big part of it. What are the
kinds of things they could tell you where you're like, oh, cool,
and it's more fun to watch because of that and
not I think where a lot of the push was
in adding tech to the sport, which is we're gonna
make it nerdier like that was the thing I don't
want to do. I'm interested in leaning in to what
(40:15):
makes this great and letting you see writ in the
classic the stats to make the invisible visible, letting you
see those things but in a narrative arc so that
you can contextualize them. You can say something more intelligent
about sport, but like it. I wasn't here to make
you feel like I changed the sport. I was here
(40:35):
to make you feel like you were spoken to more
crisply about it. You were able to speak more crisply
about it, and the fight just looked a little shinier,
a little brighter because of this kind of thing. And
like I said, when this tech does its best work,
it just disappears.
Speaker 3 (40:55):
Hearing you describe it, it strikes me that what you're
doing is you're moving people up a level.
Speaker 5 (41:01):
You're right, we are bringing it to a place where
you feel like you can you could even have an
opinion because you understand enough of what's going on. You
are one hundred percent right. We're moving everybody right right
up the scale on a daily basis. I want to
go back to INSIGHT's engine is not here to feel technical,
and that's the genius of it. It's simplicity. It's narrative
(41:23):
is the thing that allows you to bring people forward
because you're not using jargon, because you're not just into
the numbers, right, That's really that's really the key here.
Speaker 3 (41:32):
When you look back at your experience with fight data,
are there a few categories that are essential to winning?
Speaker 5 (41:40):
I think the easiest way to answer that is the
entire statistical system that we built is based on only
one question.
Speaker 4 (41:49):
We don't track style.
Speaker 5 (41:53):
For example, I don't track whether somebody hit you with
a cross or a jab. Even more ridiculous, in the
official statistics, we don't track whether we hit you with
an arm or a leg. And that's because the entire
statistical system is built on this question what moved you
closer to winning the fight? And it turns out that
(42:14):
what moves you closer to winning a fight is where
you take damage, right, and how much damage you take.
So if I hit you in the head, arm, leg
doesn't really matter, style doesn't really matter, it's did it land?
So the whole statistical system is built on that question
of how much of each of these things did you do?
These things which we have directly correlated to victory, And
(42:37):
with live statistics and the augments, we can do lefts
and rights and things like that people want to see.
But that's the fundamental question. So for the question is
what's the most important thing you could do?
Speaker 4 (42:49):
Land strikes?
Speaker 5 (42:50):
Land significant strikes to the head that's going to end
most fights. Can you end a fight with significant strikes
to the body that massively outpace your opponent?
Speaker 4 (42:58):
You can?
Speaker 5 (42:58):
There at a second level, down can And then there
are things that are a little harder to talk about
that way, if you have more ground control, that's putting
you closer to completing a submission. So that again is
the kind of thing. And obviously once we get to
the number of submission attempts you attempt, are going to
make it more likely that one of those will be successful.
(43:19):
But it is all built from this basic question of
all of our stats, does it get you closer to
winning the fight?
Speaker 2 (43:26):
Yeah?
Speaker 3 (43:27):
One last question. I know you've thought about this a lot,
which is next. What's like if I, IF I, if
I invite you back. We have this conversation five years soon. Now,
what is the fun wrinkle that you're working on.
Speaker 4 (43:40):
We have a couple of things that are in the works.
Some of them are very sideways to this, but there so.
Speaker 5 (43:49):
One of them, which we're prototyping is the ability to
bring additional voices into the mix seamlessly. So I'll give
you a perfect example. If the coaches who are on
the side and they're yelling in whatever language they are yelling,
they are attempting to influence the fight, and it is
and we do this occasionally. We'll cut to the coaches
(44:11):
camp and we'll listen to them for a moment, but
they're doing it constantly, wouldn't it be interesting to understand
what they're trying to do and what it means. So,
for example, if I'm saying you're doing great, but you're
not doing great by being encouraging. If I'm saying you
are doing great and you are doing great, what does
that mean? What is my tone of voice, what's my
level of stress? All of these kinds of things, so
(44:31):
that you could very subtly be able to distill that
information and bring it in and say, like, by the way,
if you want to know what.
Speaker 4 (44:40):
The coaches think, feels interesting? So that's like a really
nice one that's relatively close.
Speaker 3 (44:45):
Now I have a sense of the psychological context of
the coach and the athlete.
Speaker 5 (44:49):
Let's go further away, right, You said five years in
the future. I think five years in the future. I
have two beliefs. I don't believe people want to lean
forward experience, as much as everybody would love them to
want to lean forward experience. If you could watch a
Steph Curry performance and I could let you controlled the camera.
Speaker 3 (45:08):
No, I don't want to get OK.
Speaker 4 (45:09):
I don't believe that people do.
Speaker 5 (45:11):
Yeah, but that doesn't mean that those technologies don't have
a place. So people are talking about vogumetric capture or
GAUSSI and splatting, all of these kinds of things that
allow you to create three dimensional space and move through it.
Speaker 4 (45:22):
I am working on.
Speaker 5 (45:23):
I have a belief that one of the places I
can't put a camera imagine the two of us were fighting,
is right here, right in front of my face and
watching your face. And yet the explanation you want to
give of I hit Malcolm in the shoulder because he
had dropped his hand and it was open.
Speaker 4 (45:38):
Show me, make it available to me.
Speaker 5 (45:41):
Speed up that process fast enough, create the telestration tools
fast enough. And I think that in five years those
things are going to become rote and we will expect
impossible angles, all of these kinds of things to become
part of our world. We are going to have to
rethink what it means to watch to be a fan
of something. If you only watch a fifteen minute cutdown
(46:04):
of a NASCAR race, are you a fan or not
a fan?
Speaker 4 (46:07):
I don't know.
Speaker 5 (46:07):
Do you watch fifteen minute cutdown of every race? And
how do I service that person and how do I
engage with that person? If you do have this very
for you said earlier that people only watch a half
a show. For example, if you have a fragmented set
of attention, I can either fight it and rage against
the dying of the light, or I could lean into
it and try to service that person and make them
a real fan and bring them into the rest of
(46:28):
our ecosystem. And I think that that is going to
continue to happen. I think we're going to continue to
make an argument for live events, and the pull of
that one only needs to go. As I'm sure you've seen,
when you're in the room, there's nowhere you'd rather be,
and it is so interesting, even though it is so
much less good than the angles you see on television,
you can't help but look away. We're bought in on
(46:50):
that thesis. But the moment you step out of that room,
how do I give you the greatest experience possible?
Speaker 2 (46:56):
Yeah?
Speaker 3 (46:56):
Yeah, alone, Thank you very much.
Speaker 4 (47:00):
Thank you.
Speaker 3 (47:01):
You maybe want to become a UFC fan, which is
a statement I never thought I would ever say.
Speaker 4 (47:05):
I'll tell you what, Come watch one with us, Come
watch one with me?
Speaker 5 (47:08):
Yeah, I bet you walk away and you're like, I'm
not sure I watching every week, But holy moly, is
this amazing?
Speaker 3 (47:15):
Smart talks with IBM is produced by Matt Romano, Amy Gaines, McQuaid,
Trina Menino and Jake Harper. Were edited by Lacy Roberts.
Engineering by Nina Bird Lawrence, mastering by Sarah Buguire, music
by Gramoscope, Strategy by Cassidy Meyer and Sophia Derlin. Smart
Talks with IBM is a production of Pushkin Industries and
(47:36):
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 Glappo. This is a paid advertisement
from IBM. The conversations on this podcast don't necessarily represent
IBM's positions, strategies, or opinions
Speaker 5 (48:02):
And STI
Stuff To Blow Your Mind News
Hosts And Creators
Robert Lamb
Joe McCormick
Popular Podcasts
Joy 101 with Hoda Kotb
Joy is essential. And it's also elusive. You can't order it, borrow it, or simply hope it into life. But now, there's a new and exciting way to start your journey toward a more joyful existence: The Joy 101 Podcast with Hoda! Best known for her Emmy-winning work and co-anchoring Today, Hoda Kotb infuses her authenticity, curiosity, and warmth into conversations with the world’s most fascinating people. Entertainment legends, sport icons, wellness experts, and everyday folks will share how they find, allow, and experience joy. Hoda will offer her own tips and takes on seeking a more balanced, harmonious life. If you're craving inspiration, support, and useful tools to maximize your joy, tune in to these candid, uplifting, and moving on-air chats. Joy after a breakup, joy as an empty-nester, joy after loss, joy as a caretaker — Hoda's new podcast will speak to you. Joy 101 with Hoda Kotb, an iHeartPodcast.
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com