WINLINE MPKBK CIS LAN Season 5 · BO3
result vs predictionseries probability
35%65%
probability at match start · final 2:1
WW#123 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.
Dust2PsychoFace pick
58%50%
PsychoFace · 8 mapsedge PsychoFace +8%WW · 0 maps
Nukepossible decider
44%50%
PsychoFace · 5 mapsedge WW +6%WW · 0 maps
AnubisPsychoFace ban
50%50%
PsychoFace · 4 mapsnearly even +0%WW · 0 maps
MiragePsychoFace ban
38%50%
PsychoFace · 4 mapsedge WW +12%WW · 0 maps
OverpassWW ban
63%50%
PsychoFace · 4 mapsedge PsychoFace +13%WW · 0 maps
AncientWW pick
33%50%
PsychoFace · 2 mapsedge WW +17%WW · 0 maps
DefaultWW ban
50%50%
PsychoFace · 2 mapsnearly even +0%WW · 0 maps
Most likely veto scenario
1. BanPsychoFace remove Mirage
2. BanWW remove Overpass
3. PickPsychoFace take Dust2
4. PickWW take Ancient
5. BanWW remove Default
6. BanPsychoFace remove Anubis
DeciderNuke (44% / 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.
Nukeprediction missed13:4
PsychoFace 47%WW 53%
The model gave 53% on WW — the map was taken by PsychoFace.
Mirageprediction correct11:13
PsychoFace 35%WW 65%
The model gave 65% on WW — the map was taken by WW.
Dust2prediction correct16:13
PsychoFace 58%WW 42%
The model gave 58% on PsychoFace — the map was taken by PsychoFace.
Model check result
Model favoriteWW · 65%
Series resultPsychoFace 2:1
Series predictionmissed
Accuracy by map2 of 3