?
WINLINE MPKBK CIS LAN Season 8 · BO3
result vs prediction
UPGRADE#64 in the world · loss 1:2
series probability
33%67%
probability at match start · final 1:2
K27#44 in the world · win 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.
NukeUPGRADE ban
42%50%
UPGRADE · 8 mapsedge K27 +8%K27 · 22 maps
CacheK27 pick
38%52%
UPGRADE · 4 mapsedge K27 +14%K27 · 23 maps
Ancientpossible decider
70%45%
UPGRADE · 6 mapsedge UPGRADE +25%K27 · 18 maps
AnubisUPGRADE pick
60%67%
UPGRADE · 16 mapsedge K27 +7%K27 · 8 maps
MirageUPGRADE ban
38%67%
UPGRADE · 4 mapsedge K27 +29%K27 · 20 maps
Dust2K27 ban
50%38%
UPGRADE · 10 mapsedge UPGRADE +12%K27 · 9 maps
InfernoK27 ban
57%50%
UPGRADE · 3 mapsedge UPGRADE +7%K27 · 0 maps
Most likely veto scenario
1. BanUPGRADE remove Mirage
2. BanK27 remove Inferno
3. PickUPGRADE take Anubis
4. PickK27 take Cache
5. BanK27 remove Dust2
6. BanUPGRADE remove Nuke
DeciderAncient (70% / 45%)
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 correct13:10
UPGRADE 64%K27 36%
The model gave 64% on UPGRADE — the map was taken by UPGRADE.
Cacheprediction correct16:19
UPGRADE 33%K27 67%
The model gave 67% on K27 — the map was taken by K27.
Anubisprediction correct6:13
UPGRADE 43%K27 57%
The model gave 57% on K27 — the map was taken by K27.
Model check result
Model favoriteK27 · 67%
Series resultK27 1:2
Series predictioncorrect
Accuracy by map3 of 3