WINLINE MPKBK CIS LAN Season 5 · BO3
result vs prediction
BET-M#62 in the world · loss 0:2series probability
74%26%
probability at match start · final 0:2
Virtus.pro#50 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.
AncientBET-M ban
40%60%
BET-M · 6 mapsedge Virtus.pro +20%Virtus.pro · 1 map
MirageVirtus.pro pick
56%60%
BET-M · 5 mapsnearly even -4%Virtus.pro · 1 map
NukeBET-M pick
56%50%
BET-M · 5 mapsedge BET-M +6%Virtus.pro · 0 maps
InfernoVirtus.pro ban
38%50%
BET-M · 4 mapsedge Virtus.pro +12%Virtus.pro · 0 maps
Dust2Virtus.pro ban
50%60%
BET-M · 2 mapsedge Virtus.pro +10%Virtus.pro · 1 map
OverpassBET-M ban
50%60%
BET-M · 0 mapsedge Virtus.pro +10%Virtus.pro · 1 map
Most likely veto scenario
1. BanBET-M remove Overpass
2. BanVirtus.pro remove Inferno
3. PickBET-M take Nuke
4. PickVirtus.pro take Mirage
5. BanVirtus.pro remove Dust2
6. BanBET-M remove Ancient
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 missed12:16
BET-M 58%Virtus.pro 42%
The model gave 58% on BET-M — the map was taken by Virtus.pro.
Ancientprediction correct6:13
BET-M 28%Virtus.pro 72%
The model gave 72% on Virtus.pro — the map was taken by Virtus.pro.
Model check result
Model favoriteBET-M · 74%
Series resultVirtus.pro 0:2
Series predictionmissed
Accuracy by map1 of 2