?
arrow_backBack to match
NODWIN Clutch Series 9 · BO3
result vs prediction
Acend#125 in the world · win 2:1
series probability
45%55%
probability at match start · final 2:1
INOX Division#66 in the world · loss 1:2
The 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.
Dust2INOX Division pick
46%74%
Acend · 9 mapsedge INOX Division +28%INOX Division · 15 maps
NukeAcend ban
50%67%
Acend · 0 mapsedge INOX Division +17%INOX Division · 17 maps
Overpasspossible decider
30%57%
Acend · 6 mapsedge INOX Division +27%INOX Division · 10 maps
InfernoAcend pick
57%56%
Acend · 3 mapsnearly even +1%INOX Division · 12 maps
AncientAcend ban
44%64%
Acend · 5 mapsedge INOX Division +20%INOX Division · 7 maps
MirageINOX Division ban
67%50%
Acend · 11 mapsedge Acend +17%INOX Division · 0 maps
AnubisINOX Division ban
50%40%
Acend · 0 mapsedge Acend +10%INOX Division · 6 maps
Most likely veto scenario
1. BanAcend remove Nuke
2. BanINOX Division remove Mirage
3. PickAcend take Inferno
4. PickINOX Division take Dust2
5. BanINOX Division remove Anubis
6. BanAcend remove Ancient
DeciderOverpass (30% / 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.
Defaultprediction correct1:0
Acend 50%INOX Division 50%
The model gave 50% on Acend — the map was taken by Acend.
Infernoprediction missed10:13
Acend 54%INOX Division 46%
The model gave 54% on Acend — the map was taken by INOX Division.
Overpassprediction missed13:10
Acend 24%INOX Division 76%
The model gave 76% on INOX Division — the map was taken by Acend.
Model check result
Model favoriteINOX Division · 55%
Series resultAcend 2:1
Series predictionmissed
Accuracy by map1 of 3