WINLINE MPKBK CIS LAN Season 6 · BO3
result vs prediction
TDK#86 in the world · loss 1:2series probability
77%23%
probability at match start · final 1:2
BAKS#112 in the world · win 2:1The 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.
Dust2possible decider
78%43%
TDK · 14 mapsedge TDK +35%BAKS · 3 maps
OverpassTDK pick
79%40%
TDK · 15 mapsedge TDK +39%BAKS · 1 map
MirageTDK ban
47%50%
TDK · 11 mapsnearly even -3%BAKS · 2 maps
AncientBAKS ban
64%60%
TDK · 10 mapsnearly even +4%BAKS · 1 map
InfernoTDK ban
45%57%
TDK · 7 mapsedge BAKS +12%BAKS · 3 maps
AnubisBAKS ban
50%50%
TDK · 6 mapsnearly even +0%BAKS · 0 maps
DefaultBAKS pick
67%50%
TDK · 5 mapsedge TDK +17%BAKS · 0 maps
Most likely veto scenario
1. BanTDK remove Inferno
2. BanBAKS remove Anubis
3. PickTDK take Overpass
4. PickBAKS take Default
5. BanBAKS remove Ancient
6. BanTDK remove Mirage
DeciderDust2 (78% / 43%)
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.
Cacheprediction correct7:13
TDK 47%BAKS 53%
The model gave 53% on BAKS — the map was taken by BAKS.
Dust2prediction correct13:8
TDK 84%BAKS 16%
The model gave 84% on TDK — the map was taken by TDK.
Ancientprediction missed8:13
TDK 55%BAKS 45%
The model gave 55% on TDK — the map was taken by BAKS.
Model check result
Model favoriteTDK · 77%
Series resultBAKS 1:2
Series predictionmissed
Accuracy by map2 of 3