European Pro League Series 8 · BO3
result vs prediction
eternal premium#208 in the world · loss 0:2series probability
49%51%
probability at match start · final 0:2
ENCE#112 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.
MirageENCE pick
40%43%
eternal premium · 6 mapsnearly even -3%ENCE · 10 maps
Nukeeternal premium pick
50%60%
eternal premium · 8 mapsedge ENCE +10%ENCE · 6 maps
Ancienteternal premium ban
60%60%
eternal premium · 6 mapsnearly even +0%ENCE · 6 maps
InfernoENCE ban
50%43%
eternal premium · 4 mapsedge eternal premium +7%ENCE · 3 maps
AnubisENCE ban
38%60%
eternal premium · 4 mapsedge ENCE +22%ENCE · 1 map
Dust2eternal premium ban
40%50%
eternal premium · 1 mapedge ENCE +10%ENCE · 2 maps
Overpasspossible decider
60%50%
eternal premium · 1 mapedge eternal premium +10%ENCE · 2 maps
Most likely veto scenario
1. Baneternal premium remove Dust2
2. BanENCE remove Inferno
3. Picketernal premium take Nuke
4. PickENCE take Mirage
5. BanENCE remove Anubis
6. Baneternal premium remove Ancient
DeciderOverpass (60% / 50%)
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.
Anubisprediction correct5:13
eternal premium 26%ENCE 74%
The model gave 74% on ENCE — the map was taken by ENCE.
Mirageprediction missed7:13
eternal premium 50%ENCE 50%
The model gave 50% on eternal premium — the map was taken by ENCE.
Model check result
Model favoriteENCE · 51%
Series resultENCE 0:2
Series predictioncorrect
Accuracy by map1 of 2