WINLINE MPKBK CIS LAN Season 6 · BO3
result vs prediction
BET-M#65 in the world · loss 0:2series probability
54%46%
probability at match start · final 0:2
BAKS#112 in the world · win 2:0The 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.
Nukepossible decider
46%57%
BET-M · 9 mapsedge BAKS +11%BAKS · 3 maps
Dust2BAKS ban
45%38%
BET-M · 7 mapsedge BET-M +7%BAKS · 4 maps
MirageBET-M pick
58%50%
BET-M · 8 mapsedge BET-M +8%BAKS · 2 maps
AncientBET-M ban
36%67%
BET-M · 7 mapsedge BAKS +31%BAKS · 2 maps
InfernoBAKS pick
40%57%
BET-M · 6 mapsedge BAKS +17%BAKS · 3 maps
CacheBET-M ban
50%60%
BET-M · 0 mapsedge BAKS +10%BAKS · 1 map
OverpassBAKS ban
50%40%
BET-M · 0 mapsedge BET-M +10%BAKS · 1 map
Most likely veto scenario
1. BanBET-M remove Ancient
2. BanBAKS remove Dust2
3. PickBET-M take Mirage
4. PickBAKS take Inferno
5. BanBAKS remove Overpass
6. BanBET-M remove Cache
DeciderNuke (46% / 57%)
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.
Ancientprediction correct8:13
BET-M 20%BAKS 80%
The model gave 80% on BAKS — the map was taken by BAKS.
Infernoprediction correct6:13
BET-M 36%BAKS 64%
The model gave 64% on BAKS — the map was taken by BAKS.
Model check result
Model favoriteBET-M · 54%
Series resultBAKS 0:2
Series predictionmissed
Accuracy by map2 of 2