European Pro League Series 8 · BO3
result vs prediction
ARCRED#121 in the world · win 1:0series probability
60%40%
probability at match start · final 1:0
The Last Resort#159 in the world · loss 0:1The 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.
AncientThe Last Resort pick
33%60%
ARCRED · 5 mapsedge The Last Resort +27%The Last Resort · 11 maps
NukeARCRED ban
50%44%
ARCRED · 2 mapsedge ARCRED +6%The Last Resort · 14 maps
MirageThe Last Resort ban
50%27%
ARCRED · 4 mapsedge ARCRED +23%The Last Resort · 7 maps
OverpassARCRED ban
50%64%
ARCRED · 0 mapsedge The Last Resort +14%The Last Resort · 10 maps
AnubisARCRED pick
63%63%
ARCRED · 4 mapsnearly even +0%The Last Resort · 4 maps
Dust2The Last Resort ban
71%43%
ARCRED · 3 mapsedge ARCRED +28%The Last Resort · 3 maps
Infernopossible decider
60%56%
ARCRED · 1 mapnearly even +4%The Last Resort · 5 maps
Most likely veto scenario
1. BanARCRED remove Overpass
2. BanThe Last Resort remove Dust2
3. PickARCRED take Anubis
4. PickThe Last Resort take Ancient
5. BanThe Last Resort remove Mirage
6. BanARCRED remove Nuke
DeciderInferno (60% / 56%)
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.
Defaultprediction correct1:0
ARCRED 50%The Last Resort 50%
The model gave 50% on ARCRED — the map was taken by ARCRED.
Model check result
Model favoriteARCRED · 60%
Series resultARCRED 1:0
Series predictioncorrect
Accuracy by map1 of 1