Smithsonian.com

Image: Shockmotion

In case you haven’t heard, there are some basketball games going on now. It’s March Madness, the NCAA Division 1 basketball championships. Everybody’s favorite predictor of the future—Nate Silver—has his own analysis of the tournament over at The New York Times. He’s predicting Louisville, with a 23.8 percent chance of winning the tournament.

But should you drop your current picks and pick up Nate’s? He might have been 50 for 50 on election results, but how well does that translate to sports? Nate did try to predict the Super Bowl, this year. His methods suggested that the 49ers would beat the Ravens. As it happend, the Ravens edged out the 49ers, 34-31. But can he get the NCAA right? He’s been doing it for a while now. He writes:

I participated in my first N.C.A.A. tournament pool in 1992 when, as a 14-year-old, I correctly predicted sixth-seeded Michigan to reach the Final Four.

So even before Silver got famous for being good at seeing the future, he was pretty solid at basketball stats. Fast Company wrote about him, and computer-assisted betting, around this time last year:

“Three years ago, I had two things on my mind,” said Tarlow, a PhD student in Computer Science at the University of Toronto. “First, I was working on building a recommendation system similar to the ones used in the Netflix challenge. Second, I hadn’t paid attention to college basketball that year, but I needed to fill out my bracket for a pool with some friends.  At some point, it struck me that I could use the exact same recommendation algorithm I had been coding up to make my bracket predictions.”

Tarlow went on to explain how the computers fared against their human counterparts in last year’s competition. “We included three human-ish baselines: always picking the higher seed, the bracket predicted by Nate Silver, and Lee’s personal bracket.  Against that field, the machines won.” (For the uninitiated, the New York Times’ Nate Silver creates a bracket each year combining human- and computer-based systems.)

So perhaps you should bet on computers, rather than Nate, to fill out your bracket. But if you don’t have a super computer handy, Nate Silver is probably your man.

More from Smithsonian.com:

The 2012 Election’s Big Winner: Math
Using Math to Examine Iran’s Election Results
The List: March Madness at the Smithsonian