Slashdot Mirror
Computer System Makes Best Sports Bets
schliz writes to tell us that a new computer system using the "Logistic Regression Markov Chain" (LRMC) has proven to be the most efficient system at predicting sporting event outcomes. The system was tested on the 2008 US NCAA basketball season and picked all four of the finalists. "Similar to other rankings systems, LRMC uses the quality of each NCAA team's results and the strength of each team's schedule to rank teams. The method has been designed to use only basic scoreboard data, including which teams played, which team had home court advantage and the margin of victory."
The final four were also all #1s in their league. Coincidence? This has never happened before I believe and if the computer calculates odds the way the teams are ranked, then this may not always be so reliable.
The real test would be to look at the rest of the computer's bracket.
We figured out a long time ago that it's easier to elect seven judges than to elect 132 legislators.
The amount of noise involved strongly depends on which sport that is involved. Basket is a sport where a lot of points is scored, which in turn means that the noise is relatively low while football (what americans call soccer for some strange reason and what americans call football is more like rugby) has a lot of noise since the ability to score a goal there is depending a lot on luck.
This essentially means that counting points is a good way to score a basketball team while counting goals won't give much clue to how good a given football team is. You must look at other factors on a football team instead. And not all those factors can be as easily measured. Of course - the other factors are also important for a basket team. Other factors involved are the composition of players, individual player mood/health/inspiration, latest matches, history between the teams, referee behavior, weather, spectators, location, timezone etc. Add to this the element of randomness caused by the impact of the ball on a surface, player positions at certain points of the game etc.
If builders built buildings the way programmers wrote programs, then the first woodpecker would destroy civilization.
Here's the code I used
List pickFinalFour(Tournament tourney){
List finalFour = new ArrayList();
for (Division d : tourney){
Team bestTeam = null;
int minSeed = Integer.MAX_VALUE;
for (Team t : d){
if (t.getSeed()minSeed){
minSeed = t.getSeed();
minSeed = team;
}
}
finalFour.add(bestTeam);
}
return finalFour;
}
sigfault. core dumped.
That was my first thought as well. The four #1 seeds are theoretically the most likely to be in the final four, assuming they were seeded correctly, but of course unexpected things usually happen in sports so this is the first time that's occurred. But if I had to bet my life on picking the final four, I'd probably pick the four #1 seeds in any given year because even though the odds of that occuring are low, the odds of me choosing which #2 or #4 seeds displace a couple #1s as usually happens so that I pick the correct four teams are probably lower!
I'd say if these guys think their computer system is so good at making bets, can't they plug in data for the past 10 years worth of NCAA tournaments and see how well it does there?
Or better yet, don't write an academic paper on it, put up their own money, win millions over the next few years beating Vegas, then tell us about it in a press release from the Carribean island they bought with their winnings! You have $50 million in winnings to back you up and I'm a lot more likely to believe you've made a major advance!
One of our research assistants started doing something like this about ten years ago, fitting a statistical model to previous soccer match results and the home/away effect. He rounded some of us up to chip in a few pounds each week and off he went to the bookies to bet on the outcome of his model.
Now, any statistical model (such as this LRMC thing, or the techniques m'colleague used) will only give estimates of the odds. It might say that the probability of team A winning is 0.6. Now, if the bookies are offering you a return of 0.7 then it's worth a bet. If the bookies rate it 50-50 then it's not worth a bet.
The trouble is that any statistical model worth its salt is going to produce probabilities that add up to 1.0, whereas the bookies' odds can add up to 1.2 or so. That's how they play the game and make their profits.
So after a season where we made a few pennies profit, and got some press interest (including a team from BBC Tomorrow's World filming us playing football), my friend realised the best thing to do was not to bet at all.
And instead he went into the business of supplying odds to bookmakers. From where he now sits at the top of a rather large business empire!
I might pop him an email to see what his current techniques are, but back in the day it was something similar to this LRMC thing.
who's going to win the 'National today? If it can't tell me that, then no matter how technical-sounding it's algorithm is, it's not a lot of use to me.
politicians are like babies' nappies: they should both be changed regularly and for the same reasons
So I need a copy, preferably of the source, and a bookie.
3 years ago a friend of mine ran the super bowl through a football game and ended up 2 points off, does anyone know what the accuracy of those games are compared to a "real" system like this?
Are you telling me that somebody actually looked at win/loss records and margin of victory and strength of opponents to figure out which team might win? How can this be? Why did nobody ever figure out this simple algorithm before? [slaps forehead with hand] DOH!
....
Oh wait, sorry it was patented years ago, and multiple times with minute variations such as going back to strength of opponents opponents, and margin of victory of opponents against common opponents, and strength of opponents opponents opponents, and
But if you add in what they ate for breakfast, then you might have a new patentable algorithm.
I will now be taking bets on how long before mob goons put an axe through the computer, tie it to a chair, and throw it into a river.....
Knowing Google's lust for data collection, the Soviet Union is still alive and well inside the psyche of Sergey Brin....
If I had a computer that could predict sports results, I wouldn't tell anyone about it. I'd take a briefcase full of cash down to the bookmakers.
I know this is Slashdot, but why can't people RTFA before commenting? They aren't using the seeds or rankings in the program - only game stats, home quart advantage, etc. They ran it on the last 9 years of data and it picked final four teams 30% more often than analysts. (30/36 vs 23/36).
The linked article didn't mention it, but from the GA Tech web site, it said that it correctly identified several overrated teams that lost early on (like Georgetown), and underrated teams that went farther than expected (like WVU). The program picks Kansas to win this year.
Doesn't say whether the test was done on in-sample or out-of-sample data. That is, did they test using the same data that was used during development?
If so, the results are worthless. You can make a "system" that says anything you want given enough tweaking. (This is often the problem with apparently successful computer trading models).
Great sample... They should test the algorithm on maybe 80 historical seasons and maybe we will be able to see something.
I, for one, welcome our gambling overlords.
Trying to install linux on my microwave, but keep getting a kernel panic...
I heard about this last year and used their picks for this year's bracket. I'm tied for first in my pool, and 93.5% nationally in espn's bracket game. Just for comparison of how good their choices are. They had 100% on the first round day one.
Here is the paper describing the method: http://www2.isye.gatech.edu/people/faculty/Joel_Sokol/ncaa.pdf
Depends on what was that paper for.
If the paper they published is to test and prove methods to produce good quality predictions, they'll probably use out-of-sample data.
If the paper was published so they can ask grands, they'll probably use in-sample data and any other possible trick just to make look their system more efficient. Special bonus if they managed to cram a few money-producing grands like "could be used by DHS to predict potential terrorist threats", "can by applied by police to more accurately detect child pronographer", "has potential military applications" and whatever justification can have the "pirate" keyword attached.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
"The system was tested on the 2008 US NCAA basketball season and picked all four of the finalists."
On run 901, on run 666, on 10% of runs? Poppycock approach if that is all they can say about it. Read "A SEAGUL Visits the Race Track" for an example of a proper discussion of a prediction system.
"The system was tested on the 2008 US NCAA basketball season and picked all four of the finalists."
HAHAHA. Gamblers are not interested in the outcome of 8 games, gamblers are interested in the outcomes of 32 (round one) + 16 (round two) games, a useful return base. Waste of time/money after those rounds for gamblers. Fans are interested in such outcomes, and mainly tell you how they got cheated.
...the program will have a special function designed to find something nasty to say about Kansas and the computer will begin making sounds like Dick Vitale on amphetamines screaming about North Carolina, and just for good measure, Duke, even though they aren't playing.
Only then can it be true to life.
Who taught Biff Tannen how to program?
Slashdot Burying Stories About Slashdot Media Owned
1) Beating out the analysts on their predictions is no impressive feat.
2) The title references that it makes the best "sports bets", but then only goes on to say it was good at predicting who would win the game. The "winner" of the game is not only who will cover the spread in the game -- and very often in the tournament (read: multiple times, every year) the team that is considered a worse seed is FAVORED over the team with a better seed.
3) The professionals that consistently win in Vegas do so by using computers that crunch the numbers and give them a sharper # than what the oddsmakers have. But there is a lot more to it than that -- one of the major problems these professionals have is that it is impossible for them to get a significant amount of money down on these "loose" #'s before they are moved -- when you start doing this on a regular basis you find that getting the money down on the best # harder than picking the winner.
4) What most sports gamblers never realize is its all math. It has very little to do with who you think will win, and a lot more to do with what spread you are getting. You've got certain players playing at places like Bodog, Sportsbook.com and other "square" books that have low limits and deal square lines -- those players will NEVER win significant amounts of money long-term. If you are consistently taking +4 in a basketball game while a "professional" is getting +4.5, you might as well just find another hobby.
Eye On Gambling -- www.eog.com
Seeing as the final four were all the number one seeds in the Tournament the fact that the computer predicated this is not even that interesting. If it was a great algorithm/computer then the results would be in how well it picked both the highest ranked teams to win but also found the upsets. The bottom line is the computer isn't tested enough and they need to keep testing it and they will probably find that it is not very good just like all the other computer programs. My Personal Web Site