Show HN: A Monte Carlo model that called the World Cup finalists 2 weeks ago
github.com
3 threads
More discussion https://news.ycombinator.com/item?id=48919191 (38 points | day ago | 52 comments)
Luckily the English guy was wrong.
Link to preprint: https://papers.ssrn.com/abstract=7013338 Constructive feedback very much appreciated!
Did it confidently predict the same finalists consistently in every iteration? Or did it sometimes give different answers?
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.