Monday, September 26, 2011

Moneyball

I saw Moneyball over the weekend. This movie gives a fictionalized account of the how the general manager of the 2002 Oakland A's used the right kind of statistics to build a strong team with a low budget. This article on the GM Billy Beane gives a nice follow-up to the movie.

A bit surprising one can get a good movie about the math in baseball. Moneyball was based on the book by Michael Lewis with a screenplay co-written by Aaron Sorkin who also wrote the screenplay to the Social Network. Sorkin writes nerdy things well.

Moneyball is really a computer science movie. It's not about the computers themselves which play a small role, but its about taking a large amount of data and deriving the conclusions that help make the crucial decisions in developing the team.

You can also see the difference in computer science over the last decade. At the time of Moneyball, people would try many statistical models and test them out. These days via Machine Learning we give the computer the data and the results and the computer determines the right models.

Oddly enough Billy Beane's actions led to an even greater separation between the large and small market teams. The statistical ideas that Beane pushed have been adopted by the other teams. Now we've hit an equilibrium so the teams that spend more win more as well.

Oddly the New York Times ran an editorial piece Not-So-Smart Cities by Greg Lindsey yesterday arguing that cities shouldn't rely on these kinds of statistics for planning because of a failed project from the 60's. Sounds like Lindsey needs to see Moneyball.

9 comments:

  1. Amusingly, Mike Trick earlier posted about how Moneyball was a good example not of computer science, but of operations research: http://mat.tepper.cmu.edu/blog/?p=1514.

    ReplyDelete
  2. 1) Bill James, who was the first one to say seriously
    LETS LOOK AT VARIOUS BASEBALL MYTHS AND TEST THEM RIGOROUSLY should be in the hall of fame.

    2) Another team could have adapted these techniques
    earlier. (Although computers make it easier),
    Someone like Bill James and Hence Bill Beane could
    have used these techniques earlier.
    Why didn't they? Why is it so hard to overcome
    tradition?
    Especially when its so ... obvious that this will help you win.

    3) Bill James books do not require any real math
    (he was an English Major) so its not as though
    the hard part is the math.

    ReplyDelete
  3. based on recent posts here my new plan for tenure is to find the cheapest and most nearby conferences and submit to them and then spend the next few years helping boost the reputation of those conferences so that even though they will no longer be cheap by the time I go for tenure my vita will look very impressive

    ReplyDelete
  4. If you look closely at the Lindsey argument, it can be read as an argument for ML-type design as opposed to one based on fixed statistical models.

    The criticism of the town, and the analogy to the failed New York City is basically that they used fixed, incorrect models (speaking of which, why are we supposed to believe the model that BECAUSE the decentralization of fire companies 600,000 homes were lost?). The argument--which I have a gut feeling is correct--against the model city without people is that the difficult part of simulating a city is not to figure out how water will flow, or how surges in demand for electric power will affect the power grid, but to figure out human behavior.

    As an analogy, some universities lay down paths in the main quad that are kept free of snow. Others wait for students to choose the way they want to trudge through, then put planks over the footprints. Works a lot better.

    ReplyDelete
  5. The article seems to sensationalize things. It's not going to be "populated entirely by robots" the way that either most readers or the cartoonist would think. I would not call toilets that can flush without a human touching them "robots" in any realistic sense.

    ReplyDelete
  6. CSProf, 600,000 people's homes were lost, not 600,000 homes.

    ReplyDelete
  7. This time period included 1977 and the blackout and the riots and looting and massive arson that came with it. There were over a thousand fires that day. How many of the 600,000 were on that one day alone?

    ReplyDelete
  8. IDontKnowWhatScienceImDoing4:24 PM, September 28, 2011

    Lance and David, I read the Moneyball book a while ago, and IIRC, it was an economics grad who was behind the scenes working with Billy Beane, so pl. add economics to the list of fields that will use Moneyball in their recruiting ads :-)

    ReplyDelete
  9. If you look at the teams that made the playoffs this year, there's not a strong case to be made that spending more yields better results.

    ReplyDelete