?
European Pro League Series 7 · BO3
result vs prediction
Oxuji#173 in the world · loss 0:2
series probability
70%30%
probability at match start · final 0:2
Misa#115 in the world · win 2:0
The 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.
Dust2Misa pick
47%69%
Oxuji · 11 mapsedge Misa +22%Misa · 9 maps
NukeOxuji pick
69%50%
Oxuji · 12 mapsedge Oxuji +19%Misa · 6 maps
InfernoOxuji ban
33%44%
Oxuji · 8 mapsedge Misa +11%Misa · 5 maps
MirageMisa ban
60%45%
Oxuji · 6 mapsedge Oxuji +15%Misa · 7 maps
AncientMisa ban
64%50%
Oxuji · 7 mapsedge Oxuji +14%Misa · 0 maps
AnubisOxuji ban
43%38%
Oxuji · 3 mapsedge Oxuji +5%Misa · 4 maps
Defaultpossible decider
75%60%
Oxuji · 4 mapsedge Oxuji +15%Misa · 1 map
Most likely veto scenario
1. BanOxuji remove Anubis
2. BanMisa remove Ancient
3. PickOxuji take Nuke
4. PickMisa take Dust2
5. BanMisa remove Mirage
6. BanOxuji remove Inferno
DeciderDefault (75% / 60%)
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.
Nukeprediction missed9:13
Oxuji 71%Misa 29%
The model gave 71% on Oxuji — the map was taken by Misa.
Dust2prediction correct8:13
Oxuji 26%Misa 74%
The model gave 74% on Misa — the map was taken by Misa.
Model check result
Model favoriteOxuji · 70%
Series resultMisa 0:2
Series predictionmissed
Accuracy by map1 of 2