World Cup Predictor - AI model that identified champions for 10 consecutive tournaments
Show HN: For 10 World Cups, my model's 2 favorites had the champion every time
This innovative project showcases a machine learning model that has successfully predicted the World Cup champion in every tournament over the last decade. By analyzing historical data and team performance, the model consistently identifies the two most likely finalists, one of which always turns out to be the winner. The creator shares this impressive statistical achievement through a research paper on SSRN, offering a fascinating glimpse into the predictive power of data science in sports. It serves as a compelling case study for enthusiasts interested in the intersection of AI, sports analytics, and historical pattern recognition.
For 10 World Cups, my model's 2 favorites had the champion every time.
- bArray
I've updated the magic weights, and I too can get the result I want:
WEIGHTS = {
'w_xg': 0.09,
'w_goals': -0.07,
'w_star': 0.018,
'w_value': 0.18,
'w_rank': 0.4,
'w_def': -0.12,
'xga_share': 0.85,
'w_gk': 0.0042
}
$ python3 worldcup_model.py --sims 100000
2026 FIFA World Cup -- championship probabilities (100,000 simulations, from Round of 32)
1. England 11.7% *
2. France 10.0% *
3. Spain 9.3% *
4. Argentina 8.4%
5. Germany 8.1%
It's coming home!
- derdi
> 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?
- immighelper
Probably the human pseudonym of Paul the Octopus (https://en.wikipedia.org/wiki/Paul_the_Octopus).
- walthamstow
It's worth noting that there has only been 24 world cups
- mcphage
How does this paper not even mention the word "overfitting"?