European Pro League Series 9 · BO3
result vs prediction
Nexus#159 in the world · loss 1:2series probability
46%54%
probability at match start · final 1:2
mellren#94 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.
Miragemellren pick
57%70%
Nexus · 3 mapsedge mellren +13%mellren · 19 maps
Ancientpossible decider
63%67%
Nexus · 4 mapsnearly even -4%mellren · 11 maps
InfernoNexus ban
43%56%
Nexus · 3 mapsedge mellren +13%mellren · 12 maps
Dust2mellren ban
40%58%
Nexus · 6 mapsedge mellren +18%mellren · 8 maps
AnubisNexus pick
58%71%
Nexus · 8 mapsedge mellren +13%mellren · 3 maps
NukeNexus ban
40%25%
Nexus · 1 mapedge Nexus +15%mellren · 8 maps
Cachemellren ban
45%50%
Nexus · 7 mapsedge mellren +5%mellren · 0 maps
Most likely veto scenario
1. BanNexus remove Nuke
2. Banmellren remove Cache
3. PickNexus take Anubis
4. Pickmellren take Mirage
5. Banmellren remove Dust2
6. BanNexus remove Inferno
DeciderAncient (63% / 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.
Anubisprediction correct8:13
Nexus 39%mellren 61%
The model gave 61% on mellren — the map was taken by mellren.
Mirageprediction missed13:6
Nexus 34%mellren 66%
The model gave 66% on mellren — the map was taken by Nexus.
Infernoprediction correct6:13
Nexus 37%mellren 63%
The model gave 63% on mellren — the map was taken by mellren.
Model check result
Model favoritemellren · 54%
Series resultmellren 1:2
Series predictioncorrect
Accuracy by map2 of 3