Monday, March 11, 2013

Machine March Madness 2013. Want to participate?

Posted by Danny Tarlow
Lee and I have been a bit busy this March Madness season and haven't organized the Machine March Madness competition as well as we usually do.

Now it's March, and the tournament is beginning in a little over a week.

This is a post to see if people would be interested in competing this year despite the short notice (update: there appears to be plenty of interest. It's on). Scott Turner has graciously volunteered to help out with data needs (update: data posted at the Google group), and there is still starter code and the Google group available as resources.

If you'd be interested in competing, please drop me an email or leave a note in the comments. Also, if you'd like to compete, but something is holding you back, please leave a note in the comments, and we'll see what we can do.

20 comments:

Scott Turner said...

Well, I'm in, but you knew that :-)

Danny Tarlow said...

Great, it looks like Monte (from Scott's blog post) and Tim (from Google group) are also in. I should also be able to put together an entry, and I hear that TheMatrixFactorizer intends to come back to defend his title.

Andy Thompson said...

Do you have results from last year? I'd like to know how it did at predicting winners from the previous year(s)

Danny Tarlow said...

Yes, if you click through the posts labeled as march_madness, you can see a bunch of posts from past years. Unfortunately the Yahoo brackets don't stay from year to year, but the final posts from the last two years are at the links below:

http://blog.smellthedata.com/2012/04/final-2012-full-bracket-results.html

http://blog.smellthedata.com/2011/03/2011-algorithmic-march-madness-machines.html

Zachary Mayer said...

I'm in!

Andy Thompson said...

I'm in.

I was wondering if you guys have came across this data http://web1.ncaa.org/stats/StatsSrv/rankings?sportCode=MBB

Danny Tarlow said...

Great! Glad to have you on board.

And no, I hadn't seen that data before. It looks like a really nice resource! I'll add a pointer to it to the Google group thread on data sources. Thanks!

Kim Southwood said...

I would also like to submit an entry this year.

Danny Tarlow said...

Great. Keep an eye on the Google group for more info: https://groups.google.com/group/machine-march-madness

Mercer said...

I would be interested in joining this group. How do I get the user ID # and password for the Yahoo group?

Danny Tarlow said...

Great. I'll post instructions to the Google group. The deadline will be Thursday (you don't need to predict the play-in games).

Chuck said...

TheSentinel from last year here.

I am in again.

Chuck said...
This comment has been removed by the author.
joenudell said...

Hey, looks like I'm late to the party. Heard you on NPR this morning and would like to enter my Noodlebot. See my blog post and project page for some more info. If you want more details on my approach I'm happy to email them.

Danny Tarlow said...

Awesome. That should do for now... looks like quite the project. Glad you sqeaked in in time.

Danny Tarlow said...

Also, just making sure... you saw the instructions for entering the Yahoo bracket on the Google group?

joenudell said...

yep! Just joined.

Mark Gingrich said...

Hey, how do I join?

Danny Tarlow said...

Follow the instructions here:
https://groups.google.com/group/machine-march-madness/browse_thread/thread/aed24d37bcebfc67

Chuck said...

Danny,

Here is my strategy:

TheSentinel:
Similar strategy as last year. Used Ken Pomeroy's Pythag ratings with the log5 calculation to determine probability of winning the game.

Used a Monte Carlo simulation at 65 iterations which provided a few interesting upsets, Oregon over Oklahoma St. (I believe they were miss seeded myself!).

Will be interesting to see how it goes this year.