Slashdot Mirror

← Back to Stories (view on slashdot.org)

Mathematician Predicts Yankees To Dominate

Posted by CowboyNeal on from the safe-bets dept.

anthemaniac writes "Computerized projections in sports are nothing new, but Bruce Bukiet of the New Jersey Institute of Technology has developed a model that seems to work pretty well. He projects how many games a Major League Baseball team will win by factoring in how each hitter ought to do against each pitcher in every game. His crystal ball says the Yankees will win 110 games this year, a pretty safe bet, many might agree. But he also projects all the divisional winners. He claims to be right more than wrong in five of the past six years."

11 of 170 comments (clear)

  1. 110 wins? by nebaz · · Score: 5, Insightful

    It's a safe bet that the Yankees will do well, they always seem to spend almost twice as much as most other teams on talent, not to mention luring good players from other teams away to crush competition. Having said that, they have always spent such money, and not done exceptionally well as of late. 110 wins is a lot, and not many tesms have accomplished that. Safe bet? Hardly.

    --
    Rhymes that keep their secrets will unfold behind the clouds.There upon the rainbow is the answer to a neverending story
  2. I never understand these things... by krbvroc1 · · Score: 4, Informative

    Isn't here some rule or law about 'fitting a curve' to past data? Yet, the sports predictions, and many of the 'stock market systems' are all about
    finding some seemingly obvious pattern in past data. While you might come up with a 'back tested' model that matches really well,
    it doesn't mean squat for the future.

    1. Re:I never understand these things... by BridgeBum · · Score: 4, Informative

      His models have evolved over the years, but he tries to simulate actual games using both individual statistics (players batting averages, etc.) as well as team trends (how well does a player do against a specific pitcher). He uses a large Markov chain to predict state transitions (Runner on first, no outs - how often does it go to two outs? That sort of thing.) Very interesting project, it was a lot of fun to work on. (I was an undergrad working with Bruce 15 years ago, when he was first starting this project. He's kept it going for years.)

      --
      My UID is the product of 2 primes.
    2. Re:I never understand these things... by Burdell · · Score: 4, Insightful

      It is still trying to predict future results based on past performance. No matter what you predict, last year's Chipper Jones will never again face last year's Roger Clemens. Even if Clemens un-retires (again), he is not the same person, and neither is Chipper Jones. You also can't predict injuries, trades, managers' decisions, umpires' calls, weather, etc., all of which have an impact on the outcome of an individual game.

  3. Huh? by Kuukai · · Score: 4, Insightful

    While Bukiet is the first to admit he's not a baseball expert, in five out of the past six years, he says that his model has produced more correct than incorrect predictions. What? Does this even mean anything? If, say, he was right 51% percent of the time five years and wrong 90% of the time that other year, wouldn't that make his number of successes less than the expected number of successes from just guessing "win" or "lose"? I guess he's either really modest ("I don't like to brag, so I'll just say the accuracy is higher than 42%."), or a really, really bad statician.
    --
    Sendou Wave Kick!!
  4. Keeping up appearances by ScrewMaster · · Score: 4, Funny

    "Hello Mr. Bukiet"

    "It's pronounced bouquet!"

    --
    The higher the technology, the sharper that two-edged sword.
  5. Re:amazing by ScrewMaster · · Score: 5, Funny

    They did. It's called "tenure".

    --
    The higher the technology, the sharper that two-edged sword.
  6. That's nothing... by ericpi · · Score: 5, Funny

    He claims to be right more than wrong in five of the past six years.

    That's nothing: I've devloped a new mathematical algorithm that correctly predicts the outcome of the past six years with 100% accuracy.

  7. He's been way off-the-mark for years... by Golgafrinchan · · Score: 4, Interesting
    First, a link to the professor's baseball page.

    In 2006, he predicted 102 Yankee wins. They won 97. Not too bad.

    In 2005, he predicted 113 Yankee wins. They won 95. Way off.

    In 2004, he predicted 117 Yankee wins. They won 101. Way off.

    In 2003, he predicted 110 Yankee wins. They won 101. Not great.

    In other words, take this forecast with a big boulder of salt.

    --
    My userid is prime!
  8. Climate Models? by Matteo522 · · Score: 5, Insightful

    So let me get this straight..

    Climatologists use past data, computer models, and mathematical projections to support global warming and predict future results, and everyone calls it strong science based on facts. If the models are off, it's just a part of the scientific process, but the overall claim is still valid.

    But if a statistician uses past data, computer models, and mathematical projections to predict baseball results, it's dismissed as some crack job's phony science. If the models are off, it's proof that he has no idea what he's doing and how these kinds of models don't work.

    Am I missing something here?

  9. From one of his students by kenb215 · · Score: 5, Informative

    Wow, I never expected somebody that I knew to get on Slashdot. Bruce Bukiet is my Calculus II professor at NJIT.

    He mentioned this before a few times, including today after that article made it to the most popular spot on Yahoo! News. This is more of a hobby for him than an official project.

    From what he has said in the past about the model, it tends to overestimate the Yankees, among other reasons, because they often buy good players at the end of their prime. Thus the players won't play as well as they had in the past. He hasn't used it to make any bets. For the model, coming within a game or two of the actual results is considered a good prediction.

    As some people above said, the model isn't intended to be extremely accurate, and is frequently off by a significant amount. The interviews he does are more to get people interested in math, and to see how it has real use, rather than to try and show off. He used to go into more details in the past, but doesn't now because they tend to confuse the interviewer, and don't make it into the final article.

    Some pages of his own about the project are:
    http://m.njit.edu/~bukiet/baseball/baseball.html
    http://www.egrandslam.com/