European Pro League Series 7 · BO3
result vs prediction
MANA#86 in the world · loss 0:2series probability
28%72%
probability at match start · final 0:2
Oxuji#173 in the world · win 2:0The 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.
Dust2MANA pick
50%44%
MANA · 10 mapsedge MANA +6%Oxuji · 12 maps
Miragepossible decider
50%60%
MANA · 10 mapsedge Oxuji +10%Oxuji · 6 maps
NukeMANA ban
43%65%
MANA · 3 mapsedge Oxuji +22%Oxuji · 13 maps
AncientOxuji pick
20%64%
MANA · 6 mapsedge Oxuji +44%Oxuji · 7 maps
InfernoOxuji ban
50%33%
MANA · 2 mapsedge MANA +17%Oxuji · 8 maps
AnubisOxuji ban
44%43%
MANA · 5 mapsnearly even +1%Oxuji · 3 maps
DefaultMANA ban
50%75%
MANA · 0 mapsedge Oxuji +25%Oxuji · 4 maps
Most likely veto scenario
1. BanMANA remove Nuke
2. BanOxuji remove Anubis
3. PickMANA take Dust2
4. PickOxuji take Ancient
5. BanOxuji remove Inferno
6. BanMANA remove Default
DeciderMirage (50% / 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.
Ancientprediction correct13:16
MANA 11%Oxuji 89%
The model gave 89% on Oxuji — the map was taken by Oxuji.
Dust2prediction missed6:13
MANA 59%Oxuji 41%
The model gave 59% on MANA — the map was taken by Oxuji.
Model check result
Model favoriteOxuji · 72%
Series resultOxuji 0:2
Series predictioncorrect
Accuracy by map1 of 2