BracketBrains Giving Sports Bettors An Edge
Mark Hendrickson
37 comments »
It may not be sexy but BracketBrains could improve your chances of winning that office pool for this year’s NCAA basketball tournament.
The site, developed by three Stanford grads (one math, one computer science, and one industrial engineering), analyzes data collected from over 10 years of game results to predict who might win the possible face-offs during March Madness. It’s intended for both casual and professional bettors who want assistance in making their picks, but who don’t have the time or expertise to cull and analyze all the data themselves.
It works by looking at 15 factors in particular, including teams’ average margins of victory, distances from home, and winning percentages. Users can tweak the weight placed on each factor to account for personal intuitions, observations, and theories. This personalization in turn will adjust the system’s predictions, making the site more interactive than a simple prediction sheet.
The current version of BracketBrains is basically version 1.1. Testers of the beta product reportedly did well for themselves over this past year: 22% won prizes in their bracket pools, and 70% of the most serious users thought it had improved their performance.
BracketBrains can be described as a “freemium” product; users can model one region for free, but they’ll have to go for one of three paid packages to access more functionality. 3,000 paying subscribers have signed up so far.
While BracketBrains uses algorithms and historical data to determine its predictions, another site we’ve reviewed called PicksPal uses crowd sourcing to make its picks. Visitors to that site must pay to access its predictions, which are determined by the service’s most prescient users.





Lets see them use old data to predict last years results…or come even close for that matter.
If they can do that I would open my eyes, but for now I shall continue my nap.
Congratulations to the TeamRankings team on another successful launch! These guys are your go-to source when it comes to breaking down the numbers, and (for entertainment purposes only) making friendly wagers.
why do I need 10 years of data to predict this year’s result? is Baron Davis still playing for UCLA?…..
Before you judge the site, you should check it out. The tool works…their NFL product beat the spread something like 70% of the time this year. Honestly, you’ll improve your chances of winning your office pool by using this product. It’s worth a look…
Nice little Google Maps mashup I published today at
http://www.produnkhoops.com/sandbox/geo_tourn
It includes some interesting facts based on the venues and school locations including who has the best home court advantage and who jet lag might effect the most.
Awesome! Just the analytics I was looking for. Hope to crush the office pool this year.
I used this last year and crushed everyone in my office pool.
Dude, this is a sweet site. I know who’s going to win the office pool this year!
This tool actually works. I used it last year, and schooled all the boys in my office pool. Yes, after losing to me they deserve to be called boys :-).
Yup, me too. I didn’t win, but I used it and came in second in my office pool. The results speak for themselves.
i’ve been a frequent visitor of teamrankings.com for 7 years now. bracketbrains is an awesome feature on the site that i look forward to using every year. there is no other site out there that i know of that uses a “smart” way of analyzing stats/numbers to provide likely bracker winners.
Wow, this site is actually pretty useful, well done
Well who knows how they’ll do with the rest of the tournament, but they nailed the first game! Mount St. Mary’s won by 9 and BracketBrains predicted 9.6…
I still like to use my own judgement but I will be turning to this service for games were I can’t determine a clear winner.
Like it matters this year.
First time ever four number ones will be on the final four. Bummer huh
George Mason 2006, anyone? Team Rankings was on it. Made me some serious coin.
Thanks for the kind words, guys. I’m glad we’ve got some BracketBrains fans out there on TC…
Just want to clear the air with a few quick facts. Zach W., we back test all of our predictive models across more than a decade of historical NCAA games before “productizing” them. Last March, BracketBrains users, on average, correctly predicted nearly two more games in the tourney than the benchmark: the collective wisdom of the several million users of Yahoo!’s March Madness pick’em contest.
Two games better than the “wisdom of the crowd” may not sound like much, but the difference between the winning your bracket pool and being out of the running is often less than that, especially if those games are in the later rounds.
Ephraim, as much as I would love to say our analysis was 70% against the spread for NFL this past season, it wasn’t. That level of performance, assuming you issued recommendations for at least 70 or 80 games, would be approaching superhuman. However, our NFL analysis tool was just a hair under 70% picking game winners straight up, and over 61.7% against the spreads in 81 recommended games. Again, those results beat all the benchmarks we track. (See http://teamrankings.com/nfl/20.....esults.php for all the data)
And Scott W, yes, a great start to the tournament tonight for BracketBrains.com. You can never judge a predictive system using a sample size of one game, but we all took a minute for a high five/fist pump, then moved on to the analysis of Thursday’s games. Strategy guide for dominating your bracket pool will be posted tonight.
- Tom Federico, Co-founder, TeamRankings.com
TeamRankings definitely goes deeper then anything else out there for the hardcore sports fans. Glad to see these guys getting some recognition.
They’ve surely put some hardwork, although I still doubt the results
This is a great site with some serious analysis behind it. I love it!
Just be careful with playing too many pools, FBI has been cracking down on Facebook March Madness pools. It’s really a shame that our lovely politicians have outlawed some friendly wagering.
Interesting article posted today on march madness pool strategy interviewing a professor of Game Theory on making good picks.
http://www.thisistech.com/2008....._strategy/
Thanks, TechCrunch. One of the best kept secrets on the web is no longer a best kept secret. I’m hoping the folks in my pool don’t hear about BracketBrains because it’s definitely provided a competitive advantage in making my picks the last 3 years.
I’ve used BracketBrains before and found it useful — especially for the earlier rounds, saves a lot of time researching the 7-10 games and still being unsure of who to pick from a lot of subjective sportswriter analysis.
For more bracket wisdom, and for a place to put all that wisdom to use, pay us a visit at:
http://bracketboy.net
Or add the Facebook app here:
http://apps.facebook.com/bracketboy/
Great job on the product, guys– and congrats on the coverage.
Just what I need to be competitive in my office pool without loads of prep. Last year was an outlier — we can thank UNC for an epic choke. Can’t wait for this year.
I knew it was just a matter of time before everyone found out about BracketBrains and TeamRankings… Oh well. It’s a great tool, though it did not pick Florida last year.
Imagine the possibilities beyond basketball and football. These guys get it. Congrats on another great launch and upgrade!
Could you compare your site to the better half of the 7 million Yahoo brackets? I would imagine that there are literally millions of brackets that were blindly chosen by people with no effort at all.
Love this site… the “algorithm” is the only way to pick your teams
Why not use a statistical-based tool when you’re having trouble deciding on a close matchup? If you can’t decide, seems like you might as well.
Once the results gets 90% or more accurate, we’ll wonder why people even bother to play the game since we’ll already know the outcome.
Wasn’t it suppose to be about… the love of the game?