Rajiv Maheswaran: The math behind basketball's wildest moves
Rajiv Maheswaran - Researcher
Using advanced data analysis tools, Rajiv Maheswaran and Second Spectrum help make basketball teams smarter. Full bio
by the science of moving dots.
in our offices, as we shop and travel
and around the world.
if we could understand all this movement?
and insight in it.
at capturing information about ourselves.
sensors or videos, or apps,
with incredibly fine detail.
where we have the best data about movement
or football or the other football,
and our players to track their movements
is turning our athletes into --
and like most raw data,
and not that interesting.
basketball coaches want to know.
because they'd have to watch every second
the game with the eye of a coach.
shots and rebounds.
slightly more complicated.
and pick-and-rolls, and isolations.
Most casual players probably do.
the machine understands complex events
with the eyes of a coach.
something like a pick-and-roll,
it would be terrible.
in basketball between four players,
without the ball
guarding the guy with the ball,
and ta-da, it's a pick-and-roll.
of a terrible algorithm.
he's called the screener --
but he doesn't stop close enough,
and he does stop
it's probably not a pick-and-roll.
they could all be pick-and-rolls.
the distances, the locations,
we can go beyond our own ability
Well, it's by example.
"Good morning, machine.
and here are some things that are not.
features that enable it to separate.
to teach it the difference
use color or shape?"
what are those things?
the world of moving dots?
with relative and absolute location,
of moving dots, or as we like to call it,
in academic vernacular.
you have to make it sound hard --
it's not that they want to know
how it happened.
So here's a little insight.
the most important play.
and knowing how to defend it,
and losing most games.
has a great many variations
is really the thing that matters,
to be really, really good.
and two defensive players,
the pick-and-roll dance.
can either take, or he can reject.
can either go over or under.
or play up to touch, or play soft
either switch or blitz
most of these things when I started
according to those arrows.
but it turns out movement is very messy.
these variations identified
a professional coach to believe in you.
with the right spatiotemporal features
to identify these variations.
almost every single contender
on a machine that understands
that has changed strategies
very important games,
coaches who've been in the league
advice from a machine.
it's much more than the pick-and-roll.
with simple things
much of what it does,
to be smarter than me,
can a machine know more than a coach?
to take good shots.
it's a good shot.
by defenders, that's generally a bad shot.
or how bad "bad" was quantitatively.
using spatiotemporal features,
What's the angle to the basket?
What are their distances?
at how the player's moving
and we can build a model that predicts
would go in under these circumstances?
and turn it into two things:
and the quality of the shooter.
because what's TED without a bubble chart?
and the color is the position.
we have the shot probability.
bad at the bottom.
47 percent of their shots,
takes shots that an average NBA player
is that there are lots of 47s out there.
giving 100 million dollars to
how we look at players,
a couple of years ago, in the NBA finals.
there was 20 seconds left.
came up and he took a three to tie.
named Ray Allen.
They won the championship.
games in basketball.
the shot probability for every player
a rebound at every second
that we never could before.
I can't show you that video.
about 3 weeks ago.
that led to the insights.
This is Chinatown in Los Angeles,
the Ray Allen moment
that's associated with it.
of the professional players, it's us,
announcer, it's me.
chance of happening in the NBA
and a great many other things.
it took us to make that happen.
of every NBA game -- it's not that.
a professional team to track movement.
player to get insights about movement.
sports because we're moving everywhere.
the moment and let me know
any second now.
our buildings, better plan our cities.
of the science of moving dots,
we will move forward.
About the speaker:Rajiv Maheswaran - Researcher
Using advanced data analysis tools, Rajiv Maheswaran and Second Spectrum help make basketball teams smarter.
Why you should listen
Sports fans can get obsessed with stats about player performance and game-day physics. But basketball, a fluid and fast-moving game, has been tough to understand through numbers. Rajiv Maheswaran is working to change that, by offering pro basketball teams insight into game data to make better decisions. Maheswaran is the CEO and co-founder of Second Spectrum, a startup transforming sports through technology. He is also a Research Assistant Professor at the University of Southern California's Computer Science Department and a Project Leader at the Information Sciences Institute at the USC Viterbi School of Engineering, where he co-directs the Computational Behavior Group.
His research spans various aspects of multi-agent systems and distributed artificial intelligence using decision-theoretic and game-theoretic frameworks and solutions. His current interests focus on data analytics, visualization and real-time interaction to understand behavior in spatiotemporal domains. Like, say, the spatiotemporal domain around a basketball hoop.
Rajiv Maheswaran | Speaker | TED.com