European Pro League Series 7 · BO3
result vs prediction
Acend#125 in the world · win 2:1series probability
54%46%
probability at match start · final 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.
MirageAcend pick
63%63%
Acend · 12 mapsnearly even +0%Lavked · 31 map
Dust2Acend ban
46%43%
Acend · 9 mapsnearly even +3%Lavked · 19 maps
NukeAcend ban
50%55%
Acend · 0 mapsedge Lavked +5%Lavked · 18 maps
AncientLavked pick
50%80%
Acend · 6 mapsedge Lavked +30%Lavked · 11 maps
InfernoLavked ban
44%31%
Acend · 5 mapsedge Acend +13%Lavked · 9 maps
OverpassLavked ban
36%43%
Acend · 7 mapsedge Lavked +7%Lavked · 3 maps
Anubispossible decider
50%54%
Acend · 0 mapsnearly even -4%Lavked · 9 maps
Most likely veto scenario
1. BanAcend remove Nuke
2. BanLavked remove Inferno
3. PickAcend take Mirage
4. PickLavked take Ancient
5. BanLavked remove Overpass
6. BanAcend remove Dust2
DeciderAnubis (50% / 54%)
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.
Overpassprediction correct9:13
Acend 46%Lavked 54%
The model gave 54% on Lavked — the map was taken by Lavked.
Mirageprediction missed13:7
Acend 47%Lavked 53%
The model gave 53% on Lavked — the map was taken by Acend.
Dust2prediction correct13:11
Acend 53%Lavked 47%
The model gave 53% on Acend — the map was taken by Acend.
Model check result
Model favoriteAcend · 54%
Series resultAcend 2:1
Series predictioncorrect
Accuracy by map2 of 3