TED TALK: How Computers Are Replacing Coaches In The NBA
Advanced analytics are all the rage in professional sports, which makes sense. In no other industry is a person filmed literally the entire time they're doing their job, every...single...workday. Well, at least not in MOST industries. Cough cough porn cough.
Because of the staggering amount of player tracking in the NBA game, mathmen and numberologists (that's what they're called, right?) have developed algorithms capable of recognizing the precise movements of any given player in order to determine his value. This is something no scout or coach or statistician hooked up to an intravenous Adderall drip could accomplish; it's simply too much information. Computers, however, can handle it. By showing a computer what is a good shot and what isn't a good shot, for example, these machines can then scan a player's entire career determining whether or not this guy is A) a good shooter taking bad shots, B) a good shooter taking good shots, C) a bad shooter taking good shots or D) a bad shooter taking bad shots. Feel free to call that last one "The Swaggy P Corollary."
Using a bubble chart, Rajiv Maheswaran explains how collected data on player size, movement and shot selection can describe a player's value. Someone shooting 47-percent from the field isn't just a 47-percent shooter. There's way more to it than that.
"So what we can do, again, using spatiotemporal features, we looked at every shot. We can see: Where is the shot? What's the angle to the basket? Where are the defenders standing? What are their distances? What are their angles? For multiple defenders, we can look at how the player's moving and predict the shot type. We can look at all their velocities and we can build a model that predicts what is the likelihood that this shot would go in under these circumstances? So why is this important? We can take something that was shooting, which was one thing before, and turn it into two things: the quality of the shot and the quality of the shooter. So here's a bubble chart, because what's TED without a bubble chart?"
"Those are NBA players. The size is the size of the player and the color is the position. On the x-axis, we have the shot probability. People on the left take difficult shots, on the right, they take easy shots. On the [y-axis] is their shooting ability. People who are good are at the top, bad at the bottom. So for example, if there was a player who generally made 47 percent of their shots, that's all you knew before. But today, I can tell you that player takes shots that an average NBA player would make 49 percent of the time, and they are two percent worse. And the reason that's important is that there are lots of 47s out there. And so it's really important to know if the 47 that you're considering giving 100 million dollars to is a good shooter who takes bad shots or a bad shooter who takes good shots. Machine understanding doesn't just change how we look at players, it changes how we look at the game."
As if that wasn't complex/awesome enough, these algorithms can teach computers how to recognize the proper way to defend a particular player on pick and rolls, down screens, etc. They literally monitor everyone's movement on the court and determine which actions tend to yield which results. It's incredible.
Now if only they could recruit free agents...
Be the first to know
Want FREE Fantasy and Betting Advice and Savings Delivered to your Inbox? Sign up for our Newsletter.