NODWIN Clutch Series 12 · BO3
result vs prediction
Nemiga#22 in the world · win 2:1series probability
59%41%
probability at match start · final 2:1
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.
Dust2Color pick
57%65%
Nemiga · 17 mapsedge Color +8%Color · 19 maps
AncientNemiga ban
54%62%
Nemiga · 22 mapsedge Color +8%Color · 9 maps
Miragepossible decider
74%76%
Nemiga · 15 mapsnearly even -2%Color · 13 maps
AnubisNemiga pick
72%58%
Nemiga · 14 mapsedge Nemiga +14%Color · 8 maps
CacheColor ban
67%36%
Nemiga · 11 mapsedge Nemiga +31%Color · 7 maps
NukeColor ban
65%50%
Nemiga · 13 mapsedge Nemiga +15%Color · 0 maps
InfernoNemiga ban
60%55%
Nemiga · 1 mapedge Nemiga +5%Color · 7 maps
Most likely veto scenario
1. BanNemiga remove Inferno
2. BanColor remove Nuke
3. PickNemiga take Anubis
4. PickColor take Dust2
5. BanColor remove Cache
6. BanNemiga remove Ancient
DeciderMirage (74% / 76%)
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.
Cacheprediction correct13:5
Nemiga 80%Color 20%
The model gave 80% on Nemiga — the map was taken by Nemiga.
Dust2prediction correct9:13
Nemiga 39%Color 61%
The model gave 61% on Color — the map was taken by Color.
Ancientprediction missed13:10
Nemiga 42%Color 58%
The model gave 58% on Color — the map was taken by Nemiga.
Model check result
Model favoriteNemiga · 59%
Series resultNemiga 2:1
Series predictioncorrect
Accuracy by map2 of 3