Sunday, December 28, 2014

The robots have busted brackets, too

Dayton upset Ohio State in the first game of the NCAA tournament's "second round" and that means that you're bracket is already a total sh**show. So much for the private island and trip to the moon you were fixing to buy with Warren Buffett's cash.

The robots have busted brackets, too

Dayton upset Ohio State in the first game of the NCAA tournament's "second round" and that means that you're bracket is already a total sh**show. So much for the private island and trip to the moon you were fixing to buy with Warren Buffett's cash.

It happens almost every year. A VCU or a George Mason or a Butler lights the world on fire and surprises the hell out of Jay Bilas and everyone else who is armed with enough knowledge to falsely lead you to believe they're going to be more effective at selecting winners in what is, essentially, a mostly random series of events.

But, in the era of big data and analytic statistics, are the robots able to cut through all of that white noise and punditry about "grit" to see the future and predict March Madness winners more impressively than us mere mortals?

Turns out only a little. Over at PandoDaily, David Holmes spoke with some basketball nerds and big data prophets to try to figure out if Rosie would have taken down the Jetsons Family March Madness Pool.

For a computer to know what factors are most significant in creating a certain outcome it needs a ton of past data. Even though there are thousands of Division 1-A basketball games played each year, it would take millions of years of game data for a machine to make consistently accurate predictions,Tarlow told me last year. It’s the same reason that despite all of our technological advances, we’re still not very good at predicting giant earthquakes. The analysis relies on big quakes from the past, but those only happen once every hundred years or more.

Other factors related to basketball success are simply difficult to quantify, though these are related more to strategy than the “intangibles” like toughness that ESPN analysts like to go on and on about in an attempt to justify their expertise. Feng looks to his favorite team, the Michigan Wolverines, as an example: “Michigan is a particularly good passing team and they also shoot three pointers really well, which is particularly hard to play zone (a type of defense) against. That’s kind of an element that is difficult for an algorithm to capture.”

Then there’s the most obvious limitation: Basketball games are full of unpredictability and randomness — that’s the whole reason they’re fun to watch.

Basically, robots tend to beat humans because they can eliminate biases and prevent themselves from picking against Duke just because "f*** Duke." But, they're not really all that better at organizing the random nature of the sport, yet. So, for now, we can rest easy knowing that the robot wars haven't yet started started to taint the greatest water cooler tradition your office has ever reluctantly known. [PandoDaily]

About this blog
A blog tuned-in to what's happening on the Internet. Twitter. Homeland. Cat videos. Odd local stories. Ryan Gosling. You know, the important stuff.

Mare McKeever philly.com
Gabrielle Bonghi Philly.com
Nick Vadala Philly.com
Howard Gensler Daily News Tattle Columnist
Layla A. Jones philly.com
Molly Eichel
Peter Mucha Philly.com
Latest Videos:
Also on Philly.com:
Stay Connected