BRO Cyber League Season 1 · BO3
result vs prediction
DEPO#87 in the world · win 2:1series probability
81%19%
probability at match start · final 2:1
Game Point#229 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.
Dust2DEPO pick
54%43%
DEPO · 9 mapsedge DEPO +11%Game Point · 3 maps
MirageGame Point ban
55%29%
DEPO · 7 mapsedge DEPO +26%Game Point · 3 maps
AncientDEPO ban
42%40%
DEPO · 8 mapsnearly even +2%Game Point · 1 map
InfernoGame Point ban
33%50%
DEPO · 2 mapsedge Game Point +17%Game Point · 0 maps
AnubisDEPO ban
40%50%
DEPO · 1 mapedge Game Point +10%Game Point · 0 maps
Cachepossible decider
60%50%
DEPO · 1 mapedge DEPO +10%Game Point · 0 maps
OverpassGame Point pick
60%50%
DEPO · 1 mapedge DEPO +10%Game Point · 0 maps
Most likely veto scenario
1. BanDEPO remove Anubis
2. BanGame Point remove Inferno
3. PickDEPO take Dust2
4. PickGame Point take Overpass
5. BanGame Point remove Mirage
6. BanDEPO remove Ancient
DeciderCache (60% / 50%)
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.
Infernoprediction missed13:5
DEPO 31%Game Point 69%
The model gave 69% on Game Point — the map was taken by DEPO.
Dust2prediction missed11:13
DEPO 64%Game Point 36%
The model gave 64% on DEPO — the map was taken by Game Point.
Ancientprediction correct16:14
DEPO 52%Game Point 48%
The model gave 52% on DEPO — the map was taken by DEPO.
Model check result
Model favoriteDEPO · 81%
Series resultDEPO 2:1
Series predictioncorrect
Accuracy by map1 of 3