European Pro League Series 7 · BO3
result vs predictionseries probability
76%24%
probability at match start · final 2:1
MANA#86 in the world · loss 1:2The 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.
MirageLavked pick
61%54%
Lavked · 29 mapsedge Lavked +7%MANA · 9 maps
Dust2MANA pick
43%46%
Lavked · 17 mapsnearly even -3%MANA · 9 maps
NukeMANA ban
55%43%
Lavked · 18 mapsedge Lavked +12%MANA · 3 maps
AncientMANA ban
80%20%
Lavked · 11 mapsedge Lavked +60%MANA · 6 maps
Anubispossible decider
50%50%
Lavked · 8 mapsnearly even +0%MANA · 4 maps
InfernoLavked ban
31%50%
Lavked · 9 mapsedge MANA +19%MANA · 2 maps
OverpassLavked ban
43%40%
Lavked · 3 mapsnearly even +3%MANA · 1 map
Most likely veto scenario
1. BanLavked remove Inferno
2. BanMANA remove Ancient
3. PickLavked take Mirage
4. PickMANA take Dust2
5. BanMANA remove Nuke
6. BanLavked remove Overpass
DeciderAnubis (50% / 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.
Mirageprediction correct19:17
Lavked 60%MANA 40%
The model gave 60% on Lavked — the map was taken by Lavked.
Dust2prediction correct8:13
Lavked 44%MANA 56%
The model gave 56% on MANA — the map was taken by MANA.
Anubisprediction correct13:11
Lavked 50%MANA 50%
The model gave 50% on Lavked — the map was taken by Lavked.
Model check result
Model favoriteLavked · 76%
Series resultLavked 2:1
Series predictioncorrect
Accuracy by map3 of 3