NODWIN Clutch Series 8 · BO3
result vs prediction
AM#57 in the world · loss 0:2series probability
52%48%
probability at match start · final 0:2
SPARTA#96 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.
Dust2SPARTA pick
33%54%
AM · 2 mapsedge SPARTA +21%SPARTA · 9 maps
AncientAM ban
43%33%
AM · 3 mapsedge AM +10%SPARTA · 5 maps
MirageAM ban
50%40%
AM · 2 mapsedge AM +10%SPARTA · 6 maps
NukeSPARTA ban
50%50%
AM · 4 mapsnearly even +0%SPARTA · 4 maps
InfernoSPARTA ban
71%50%
AM · 3 mapsedge AM +21%SPARTA · 4 maps
OverpassAM pick
67%57%
AM · 2 mapsedge AM +10%SPARTA · 3 maps
Defaultpossible decider
60%40%
AM · 1 mapedge AM +20%SPARTA · 1 map
Most likely veto scenario
1. BanAM remove Ancient
2. BanSPARTA remove Inferno
3. PickAM take Overpass
4. PickSPARTA take Dust2
5. BanSPARTA remove Nuke
6. BanAM remove Mirage
DeciderDefault (60% / 40%)
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.
Dust2prediction correct6:13
AM 28%SPARTA 72%
The model gave 72% on SPARTA — the map was taken by SPARTA.
Nukeprediction missed8:13
AM 53%SPARTA 47%
The model gave 53% on AM — the map was taken by SPARTA.
Model check result
Model favoriteAM · 52%
Series resultSPARTA 0:2
Series predictionmissed
Accuracy by map1 of 2