NODWIN Clutch Series 9 · BO3
result vs prediction
SPARTA#96 in the world · loss 1:2series probability
63%37%
probability at match start · final 1:2
AM#57 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.
Dust2AM ban
60%25%
SPARTA · 16 mapsedge SPARTA +35%AM · 8 maps
MirageAM pick
36%57%
SPARTA · 10 mapsedge AM +21%AM · 10 maps
NukeAM ban
50%53%
SPARTA · 8 mapsnearly even -3%AM · 11 maps
AncientSPARTA ban
29%33%
SPARTA · 10 mapsnearly even -4%AM · 8 maps
InfernoSPARTA ban
40%60%
SPARTA · 6 mapsedge AM +20%AM · 6 maps
OverpassSPARTA pick
56%70%
SPARTA · 5 mapsedge AM +14%AM · 6 maps
Defaultpossible decider
40%60%
SPARTA · 1 mapedge AM +20%AM · 1 map
Most likely veto scenario
1. BanSPARTA remove Ancient
2. BanAM remove Dust2
3. PickSPARTA take Overpass
4. PickAM take Mirage
5. BanAM remove Nuke
6. BanSPARTA remove Inferno
DeciderDefault (40% / 60%)
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.
Mirageprediction missed13:6
SPARTA 32%AM 68%
The model gave 68% on AM — the map was taken by SPARTA.
Nukeprediction correct6:13
SPARTA 44%AM 56%
The model gave 56% on AM — the map was taken by AM.
Overpassprediction correct2:13
SPARTA 35%AM 65%
The model gave 65% on AM — the map was taken by AM.
Model check result
Model favoriteSPARTA · 63%
Series resultAM 1:2
Series predictionmissed
Accuracy by map2 of 3