?
European Pro League Series 9 · BO3
result vs prediction
Drama#142 in the world · loss 1:2
series probability
51%49%
probability at match start · final 1:2
mellren#91 in the world · win 2:1
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.
MirageDrama pick
63%65%
Drama · 4 mapsnearly even -2%mellren · 13 maps
Ancientmellren ban
60%55%
Drama · 6 mapsedge Drama +5%mellren · 7 maps
Infernomellren pick
43%62%
Drama · 3 mapsedge mellren +19%mellren · 9 maps
Dust2Drama ban
29%55%
Drama · 3 mapsedge mellren +26%mellren · 7 maps
Nukemellren ban
71%29%
Drama · 3 mapsedge Drama +42%mellren · 3 maps
AnubisDrama ban
40%71%
Drama · 1 mapedge mellren +31%mellren · 3 maps
Defaultpossible decider
60%60%
Drama · 1 mapnearly even +0%mellren · 1 map
Most likely veto scenario
1. BanDrama remove Anubis
2. Banmellren remove Nuke
3. PickDrama take Mirage
4. Pickmellren take Inferno
5. Banmellren remove Ancient
6. BanDrama remove Dust2
DeciderDefault (60% / 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.
Nukeprediction correct13:8
Drama 88%mellren 12%
The model gave 88% on Drama — the map was taken by Drama.
Infernoprediction correct7:13
Drama 29%mellren 71%
The model gave 71% on mellren — the map was taken by mellren.
Mirageprediction correct7:13
Drama 48%mellren 52%
The model gave 52% on mellren — the map was taken by mellren.
Model check result
Model favoriteDrama · 51%
Series resultmellren 1:2
Series predictionmissed
Accuracy by map3 of 3