WINLINE MPKBK CIS LAN Season 5 · BO3
result vs prediction
K27#44 in the world · win 2:1series probability
60%40%
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.
Dust2PsychoFace pick
40%55%
K27 · 1 mapedge PsychoFace +15%PsychoFace · 7 maps
MiragePsychoFace ban
40%38%
K27 · 1 mapnearly even +2%PsychoFace · 4 maps
OverpassK27 pick
50%71%
K27 · 2 mapsedge PsychoFace +21%PsychoFace · 3 maps
AnubisK27 ban
50%50%
K27 · 0 mapsnearly even +0%PsychoFace · 4 maps
NukePsychoFace ban
40%29%
K27 · 1 mapedge K27 +11%PsychoFace · 3 maps
Ancientpossible decider
33%40%
K27 · 2 mapsedge PsychoFace +7%PsychoFace · 1 map
DefaultK27 ban
50%50%
K27 · 0 mapsnearly even +0%PsychoFace · 2 maps
Most likely veto scenario
1. BanK27 remove Anubis
2. BanPsychoFace remove Nuke
3. PickK27 take Overpass
4. PickPsychoFace take Dust2
5. BanPsychoFace remove Mirage
6. BanK27 remove Default
DeciderAncient (33% / 40%)
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 missed6:13
K27 60%PsychoFace 40%
The model gave 60% on K27 — the map was taken by PsychoFace.
Overpassprediction missed13:5
K27 31%PsychoFace 69%
The model gave 69% on PsychoFace — the map was taken by K27.
Ancientprediction missed13:4
K27 43%PsychoFace 57%
The model gave 57% on PsychoFace — the map was taken by K27.
Model check result
Model favoriteK27 · 60%
Series resultK27 2:1
Series predictioncorrect
Accuracy by map0 of 3