European Pro League Series 8 · BO3
result vs prediction
ENCE#112 in the world · loss 0:2series probability
31%69%
probability at match start · final 0:2
SPARTA#96 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.
Dust2ENCE ban
50%57%
ENCE · 2 mapsedge SPARTA +7%SPARTA · 26 maps
MirageSPARTA pick
47%47%
ENCE · 11 mapsnearly even +0%SPARTA · 15 maps
AncientSPARTA ban
60%32%
ENCE · 6 mapsedge ENCE +28%SPARTA · 15 maps
NukeENCE pick
60%50%
ENCE · 6 mapsedge ENCE +10%SPARTA · 14 maps
InfernoENCE ban
43%50%
ENCE · 3 mapsedge SPARTA +7%SPARTA · 8 maps
Overpasspossible decider
50%45%
ENCE · 2 mapsedge ENCE +5%SPARTA · 7 maps
AnubisSPARTA ban
67%50%
ENCE · 2 mapsedge ENCE +17%SPARTA · 2 maps
Most likely veto scenario
1. BanENCE remove Dust2
2. BanSPARTA remove Anubis
3. PickENCE take Nuke
4. PickSPARTA take Mirage
5. BanSPARTA remove Ancient
6. BanENCE remove Inferno
DeciderOverpass (50% / 45%)
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 missed8:13
ENCE 79%SPARTA 21%
The model gave 79% on ENCE — the map was taken by SPARTA.
Mirageprediction correct7:13
ENCE 46%SPARTA 54%
The model gave 54% on SPARTA — the map was taken by SPARTA.
Model check result
Model favoriteSPARTA · 69%
Series resultSPARTA 0:2
Series predictioncorrect
Accuracy by map1 of 2