WINLINE MPKBK CIS LAN Season 9 · BO3
result vs prediction
K27#44 in the world · win 2:1series probability
80%20%
probability at match start · final 2:1
WW#125 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.
MirageK27 pick
67%53%
K27 · 20 mapsedge K27 +14%WW · 13 maps
CacheWW ban
53%44%
K27 · 26 mapsedge K27 +9%WW · 5 maps
Dust2K27 ban
43%48%
K27 · 10 mapsedge WW +5%WW · 19 maps
NukeK27 ban
50%63%
K27 · 20 mapsedge WW +13%WW · 4 maps
AncientWW ban
43%40%
K27 · 17 mapsnearly even +3%WW · 6 maps
Anubispossible decider
69%55%
K27 · 9 mapsedge K27 +14%WW · 7 maps
DefaultWW pick
60%50%
K27 · 1 mapedge K27 +10%WW · 0 maps
Most likely veto scenario
1. BanK27 remove Dust2
2. BanWW remove Ancient
3. PickK27 take Mirage
4. PickWW take Default
5. BanWW remove Cache
6. BanK27 remove Nuke
DeciderAnubis (69% / 55%)
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.
Dust2prediction correct9:13
K27 42%WW 58%
The model gave 58% on WW — the map was taken by WW.
Nukeprediction missed13:3
K27 40%WW 60%
The model gave 60% on WW — the map was taken by K27.
Mirageprediction correct13:11
K27 64%WW 36%
The model gave 64% on K27 — the map was taken by K27.
Model check result
Model favoriteK27 · 80%
Series resultK27 2:1
Series predictioncorrect
Accuracy by map2 of 3