Tipsport Open Cup 1 · BO3
result vs prediction
eSuba#293 in the world · loss 0:2series probability
22%78%
probability at match start · final 0:2
BRUTE#74 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.
Dust2BRUTE pick
29%60%
eSuba · 3 mapsedge BRUTE +31%BRUTE · 16 maps
NukeeSuba ban
43%50%
eSuba · 3 mapsedge BRUTE +7%BRUTE · 12 maps
InfernoeSuba pick
56%64%
eSuba · 5 mapsedge BRUTE +8%BRUTE · 7 maps
MirageeSuba ban
60%57%
eSuba · 1 mapnearly even +3%BRUTE · 10 maps
AnubisBRUTE ban
38%38%
eSuba · 4 mapsnearly even +0%BRUTE · 4 maps
Cachepossible decider
50%33%
eSuba · 0 mapsedge eSuba +17%BRUTE · 5 maps
AncientBRUTE ban
50%50%
eSuba · 4 mapsnearly even +0%BRUTE · 0 maps
Most likely veto scenario
1. BaneSuba remove Mirage
2. BanBRUTE remove Ancient
3. PickeSuba take Inferno
4. PickBRUTE take Dust2
5. BanBRUTE remove Anubis
6. BaneSuba remove Nuke
DeciderCache (50% / 33%)
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.
Anubisprediction missed8:13
eSuba 53%BRUTE 47%
The model gave 53% on eSuba — the map was taken by BRUTE.
Dust2prediction correct4:13
eSuba 19%BRUTE 81%
The model gave 81% on BRUTE — the map was taken by BRUTE.
Model check result
Model favoriteBRUTE · 78%
Series resultBRUTE 0:2
Series predictioncorrect
Accuracy by map1 of 2