Home > data science > When accurate modeling is not good

When accurate modeling is not good

December 12, 2012

I liked Andrew Gelman’s recent post (hat tip Suresh Naidu) about predatory modeling going on in casinos, specifically Caesars in Iowa. The title of the post is already good, and is a riff on Caesars Entertainment CEO Gary Loveman said:

There are four ways to get fired from Caesars: (1) theft, (2) sexual harassment, (3) running an experiment without a control group, and (4) keeping a gambling addict away from the casino

He tells a story about a woman who loses lots of money at the casino, but who moreover gets manipulated to come back and lose more and more based on the data the people collected at Caesars and based on the models built by the quants there. You should read the whole thing, which as usual with Gelman is quirky and fun. His main point comes here (emphasis mine):

The Caesars case (I keep wanting to write Caesar’s but apparently no, it’s Caesars, just like Starbucks) interested me because of the role of statistics. I’m used to thinking of probability and statistics as a positive social force (helping medical research or, in earlier days, helping the allies in World War 2), or mildly positive (for example, helping design measures to better evaluate employees), or maybe neutral (exotic financial instruments which serve no redeeming social value but presumably don’t do much harm) or moderately negative (“Moneyball”-style strategies such as going for slow sluggers who foul off endless pitches and walk a lot; it may win games but it makes for boring baseball). And then there are statisticians who do fishy analyses, for example trying to hide that some drug causes damage so it can stay on the market. But that’s a bit different because such a statistical analysis, no matter how crafty, is inherently a bad analysis, trying to obscure rather than learn.

The Caesars case seems different, in that there is a very direct tradeoff: the better the statistics and the better the science, the worse the human outcomes. These guys are directly optimizing their ability to ruin some people’s lives.

It’s not the only one, but they are not usually this clear-cut.

It’s time we started scoring models on various dimensions. Accuracy is one, predatoriness is another. They’re distinct.

Categories: data science
  1. Emanuel Derman
    December 12, 2012 at 7:55 am

    Are there any applications of Big Data that aren’t manipulative?


    • December 12, 2012 at 10:22 am

      I’ve made it easier for people to find local businesses on Google and Google maps with big data. Depends on how you frame it, maybe that is just manipulating people into wasting less time.


  2. mathematrucker
    December 12, 2012 at 9:09 am

    A good non-technical read on this subject is given by WSJ reporter Christina Binkley in her first book – which is both informative and entertaining – “Winner Takes All: Steve Wynn, Kirk Kerkorian, Gary Loveman, and the Race to Own Las Vegas:”


    Back in 2009 when this book was published Caesars Entertainment was called Harrah’s (apostrophe included) Entertainment.

    I suspect Binkley’s book probably played a direct role in the PR decision that placed Gary Loveman on everyone’s TV screen as the sweet guy who just wants everyone to have a good time and “play responsibly”.

    Loveman’s quant crew at Harrah’s pioneered casino-data science. Binkley tells the story well.


  3. December 12, 2012 at 10:27 am

    Where is the personal responsibility? I think that sometimes, when people f things up, you just have to blame them. If I am consistently pissing away my money at the casino, the fault lies not with the casino, but with me. Making a bunch of clearly negative expected value bets is dumb. It’s my fault for taking them, not the opposing sides fault for offering them.


    • JSE
      December 12, 2012 at 2:47 pm

      “Where is the personal responsibility? I think that sometimes, when people f things up, you just have to blame them.”

      Yes. Sometimes. But not all the time.


  4. December 12, 2012 at 12:27 pm

    Government-approved gambling casinos (including untaxed Wall Street contingent claims markets) are copouts for appropriately taxing the rich, and are enabling addiction-unto-poverty without requiring funding for its medical treatment – one more corruption of a society that has little claim to be a civilization.


  5. Jonathan
    December 12, 2012 at 3:16 pm

    He is extremely naive that it just occurred to him that statistics can be used for bad purposes.

    I seriously doubt that you can be fired from Caesars for sexual harassment. Loveman is just saying that to be politically correct.

    Statistics did not make baseball more boring. The same analysis that tells you to hire batters who draw a lot of walks tells you to hire pitchers who don’t give them up. Its that they tolerate batters who adjust their batting glove three times between every pitch that are the problem.


  6. libertarian by default
    December 12, 2012 at 3:48 pm

    I don’t understand the hate here. The casino uses quantitative analysis to improve its profits, just like every other enterprise in the modern age (and in total that makes all of us a lot better off due to better efficiency). Note that the casino is selling entertainment which the consumers voluntarily purchase, and that its profits are not magically destroyed (i.e. statistics did something terrible) but feed back into society via taxes and e.g. dividends to shareholders.

    If you want to argue that gambling should be illegal and disproportionately hurts the poor then I’m open to that debate (disagree that we want such a paternalistic state) but I don’t see why if you think casinos should exist at all you wouldn’t expect them to entice people to “purchase more of their product” (i.e. more gambling) like every other company.


    • mathematrucker
      December 16, 2012 at 12:23 am

      Libertarian definition of the word “nuance”: twin uncles marrying in a double wedding.


  7. Robito
    December 14, 2012 at 5:41 am

    If you substitute “Goldman Sachs” for “Caesars” the only thing that changes is that the victims are entire nations.


  1. December 13, 2012 at 7:13 am
Comments are closed.
%d bloggers like this: