13 comments

  • malthaus a minute ago

    now back your claim with money and bet accordingly on betting sites to see if you uncovered some actual alpha here

  • derdi 21 minutes ago

    > Applied prospectively to the in-progress 2026 World Cup from the Round of 32, the model identifies Argentina (28.0%) and Spain (21.1%) as the leading championship candidates.

    Seems weird to wait to run the "prospective" simulation until the World Cup is already in progress. Although it seems that the model also needs to use "the actual bracket and group-stage performance". So it's not prospective?

      swiftcoder 11 minutes ago

      It predicts likely winners based on the round of 32 performance (plus prior data). That's still "prospective" with respect to the finals

        derdi 3 minutes ago

        Yes. I don't like phrasing this as being prospective for the World Cup as a whole. It's for the knockout stage. (Which the abstract says! But the title doesn't.)

  • immighelper 22 minutes ago

    Probably the human pseudonym of Paul the Octopus (https://en.wikipedia.org/wiki/Paul_the_Octopus).

  • walthamstow 22 minutes ago

    It's worth noting that there has only been 24 world cups

  • mikelward 21 minutes ago

    > the model identifies Argentina (28.0%) and Spain (21.1%) as the leading championship candidates

  • dwedge 25 minutes ago

    A good AI would calculate refereeing decisions and put Argentina at 100% unless England can pull off a miracle against FIFA today.

  • dwedge 30 minutes ago

    !remindme tomorrow

  • mcphage 30 minutes ago

    How does this paper not even mention the word "overfitting"?

      dmurray 23 minutes ago

      The abstract does say

      > limitations, principally the small number of tournaments available for validation and the risk of in-sample weight selection

      But I agree this model is no more valuable than Paul the Octopus.

        mcphage 8 minutes ago

        That almost makes it worse—like they're vaguely aware that training too heavily on too small a data set makes badly trained models, but are unaware that it has a name and is an actual identified problem.

  • killingtime74 25 minutes ago

    "They've done studies, you know. 60% of the time, it works every time." - Brian Fantana, Anchorman