European Pro League Series 8 · BO3
result vs prediction
1win#33 in the world · win 2:0series probability
45%55%
probability at match start · final 2:0
GenOne#95 in the world · loss 0:2The prediction was locked in using data as of the match start: map winrates, form and head-to-head were computed only from games before it began. This is how the model's honest accuracy is verified.
Map veto prediction
For each map — both teams' winrate over 3 months. The model guesses who bans it and who keeps it: teams remove maps where they are weaker and pull toward their strong ones.
Dust21win pick
70%68%
1win · 6 mapsnearly even +2%GenOne · 43 maps
Nuke1win ban
50%60%
1win · 0 mapsedge GenOne +10%GenOne · 26 maps
Ancient1win ban
43%46%
1win · 3 mapsnearly even -3%GenOne · 22 maps
OverpassGenOne ban
33%37%
1win · 5 mapsnearly even -4%GenOne · 15 maps
Infernopossible decider
67%56%
1win · 2 mapsedge 1win +11%GenOne · 14 maps
AnubisGenOne pick
57%57%
1win · 3 mapsnearly even +0%GenOne · 10 maps
MirageGenOne ban
33%50%
1win · 8 mapsedge GenOne +17%GenOne · 0 maps
Most likely veto scenario
1. Ban1win remove Nuke
2. BanGenOne remove Mirage
3. Pick1win take Dust2
4. PickGenOne take Anubis
5. BanGenOne remove Overpass
6. Ban1win remove Ancient
DeciderInferno (67% / 56%)
Prediction by map vs result
Probabilities were locked in using statistics as of the match start (map winrate over the 3 months before it). We compare against the actual result of each map.
Ancientprediction missed13:6
1win 50%GenOne 50%
The model gave 50% on GenOne — the map was taken by 1win.
Cacheprediction missed13:9
1win 47%GenOne 53%
The model gave 53% on GenOne — the map was taken by 1win.
Model check result
Model favoriteGenOne · 55%
Series result1win 2:0
Series predictionmissed
Accuracy by map0 of 2