?
European Pro League Series 8 Closed Qualifier · BO3
result vs prediction
DONSTU#221 in the world · win 2:1
series probability
42%58%
probability at match start · final 2:1
Fortress#236 in the world · loss 1:2
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.
AnubisDONSTU pick
50%50%
DONSTU · 12 mapsnearly even +0%Fortress · 0 maps
Dust2Fortress ban
43%60%
DONSTU · 10 mapsedge Fortress +17%Fortress · 1 map
InfernoDONSTU ban
40%38%
DONSTU · 6 mapsnearly even +2%Fortress · 4 maps
Ancientpossible decider
50%67%
DONSTU · 6 mapsedge Fortress +17%Fortress · 2 maps
NukeFortress ban
43%40%
DONSTU · 3 mapsnearly even +3%Fortress · 1 map
OverpassFortress pick
60%67%
DONSTU · 1 mapedge Fortress +7%Fortress · 2 maps
MirageDONSTU ban
50%33%
DONSTU · 0 mapsedge DONSTU +17%Fortress · 2 maps
Most likely veto scenario
1. BanDONSTU remove Mirage
2. BanFortress remove Nuke
3. PickDONSTU take Anubis
4. PickFortress take Overpass
5. BanFortress remove Dust2
6. BanDONSTU remove Inferno
DeciderAncient (50% / 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.
Infernoprediction correct4:13
DONSTU 50%Fortress 50%
The model gave 50% on Fortress — the map was taken by Fortress.
Anubisprediction correct13:7
DONSTU 53%Fortress 47%
The model gave 53% on DONSTU — the map was taken by DONSTU.
Cacheprediction correct13:5
DONSTU 50%Fortress 50%
The model gave 50% on DONSTU — the map was taken by DONSTU.
Model check result
Model favoriteFortress · 58%
Series resultDONSTU 2:1
Series predictionmissed
Accuracy by map3 of 3