European Pro League Series 7 Closed Qualifier · BO3
result vs predictionseries probability
33%67%
probability at match start · final 1:2
Atreides#147 in the world · win 2:1The 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.
MirageENCE pick
75%75%
ENCE · 4 mapsnearly even +0%Atreides · 8 maps
OverpassENCE ban
50%45%
ENCE · 2 mapsedge ENCE +5%Atreides · 7 maps
AncientAtreides pick
50%70%
ENCE · 2 mapsedge Atreides +20%Atreides · 6 maps
InfernoENCE ban
33%67%
ENCE · 2 mapsedge Atreides +34%Atreides · 5 maps
Dust2Atreides ban
60%29%
ENCE · 1 mapedge ENCE +31%Atreides · 3 maps
Nukepossible decider
60%67%
ENCE · 1 mapedge Atreides +7%Atreides · 2 maps
AnubisAtreides ban
60%50%
ENCE · 1 mapedge ENCE +10%Atreides · 0 maps
Most likely veto scenario
1. BanENCE remove Inferno
2. BanAtreides remove Anubis
3. PickENCE take Mirage
4. PickAtreides take Ancient
5. BanAtreides remove Dust2
6. BanENCE remove Overpass
DeciderNuke (60% / 67%)
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.
Dust2prediction missed4:13
ENCE 77%Atreides 23%
The model gave 77% on ENCE — the map was taken by Atreides.
Nukeprediction missed13:10
ENCE 46%Atreides 54%
The model gave 54% on Atreides — the map was taken by ENCE.
Mirageprediction missed4:13
ENCE 50%Atreides 50%
The model gave 50% on ENCE — the map was taken by Atreides.
Model check result
Model favoriteAtreides · 67%
Series resultAtreides 1:2
Series predictioncorrect
Accuracy by map0 of 3