The Official March Madness Predictive Analytics Challenge

blog.smellthedata.com

14 points·imleeeee··6 comments

"must be based on historical data"... what about crowdsourced predictive analysis? Something like stocktwits for real-time investment ideas - analyze what people think about games for Twitter, although that would only work during each successive round and not for filling out a bracket at the very beginning. I could see that working since anyone who takes the time to tweet "team x over team y" is self-filtering for game predictive knowledge. Thoughts?

your idea sounds interesting, but i think it's getting at a different comparison. as presented, the contest is about who can design an algorithm to get the most out of a set (but large) quantity of data.

what you're suggesting is where to get the best data from. i think it's also an interesting question, but it would need to be in a separate category at the very least. also, wouldn't the best bet (pun intended) just be to go with the bookie odds? people who are putting money on the games presumably have better information than somebody just tweeting their prediction.

If I went to the effort of doing this I'd probably also find somewhere to bet real money on my picks.

You think you can build a model that is better than the bookies's?

Highly unlikely. I might be able to beat the local bar's betting circle though.

Awesome

Reply on news.ycombinator.com