News for hackers. Stuff that matters.
Re:Show HN: A Monte Carlo model that called the World Cup fi... by fabioricardo7 on Wednesday July 15, 2026 @07:12PM (#48928425)
Link to preprint: https://papers.ssrn.com/abstract=7013338 Constructive feedback very much appreciated!
Re:Show HN: A Monte Carlo model that called the World Cup fi... by trencedamp on Thursday July 16, 2026 @04:27AM (#48931753)
Did it confidently predict the same finalists consistently in every iteration? Or did it sometimes give different answers?
Re:Show HN: A Monte Carlo model that called the World Cup fi... by fabioricardo7 on Thursday July 16, 2026 @04:39AM (#48931868)
Thanks for your question. It's Monte Carlo, so individual simulated tournaments produce all sorts of champions, Argentina wins ~28% of the 100k iterations. What's stable is the aggregate: Argentina and Spain consistently come out as the two highest-probability teams, and that barely moves across different seeds.
Re:Show HN: A Monte Carlo model that called the World Cup fi... by gus_massa on Thursday July 16, 2026 @01:56PM (#48937910)
More discussion https://news.ycombinator.com/item?id=48919191 (38 points | day ago | 52 comments)

Luckily the English guy was wrong.