?
arrow_backBack to match
WINLINE MPKBK CIS LAN Season 7 · BO3
result vs prediction
Nemiga#21 in the world · win 2:1
series probability
76%24%
probability at match start · final 2:1
Black Phoenix#58 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.
Dust2Black Phoenix pick
56%54%
Nemiga · 14 mapsnearly even +2%Black Phoenix · 31 map
MirageNemiga pick
73%45%
Nemiga · 11 mapsedge Nemiga +28%Black Phoenix · 18 maps
Nukepossible decider
57%52%
Nemiga · 10 mapsedge Nemiga +5%Black Phoenix · 17 maps
AnubisBlack Phoenix ban
73%13%
Nemiga · 11 mapsedge Nemiga +60%Black Phoenix · 12 maps
AncientBlack Phoenix ban
50%40%
Nemiga · 18 mapsedge Nemiga +10%Black Phoenix · 1 map
CacheNemiga ban
64%64%
Nemiga · 7 mapsnearly even +0%Black Phoenix · 10 maps
InfernoNemiga ban
60%63%
Nemiga · 1 mapnearly even -3%Black Phoenix · 12 maps
Most likely veto scenario
1. BanNemiga remove Inferno
2. BanBlack Phoenix remove Anubis
3. PickNemiga take Mirage
4. PickBlack Phoenix take Dust2
5. BanBlack Phoenix remove Ancient
6. BanNemiga remove Cache
DeciderNuke (57% / 52%)
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 missed10:13
Nemiga 96%Black Phoenix 4%
The model gave 96% on Nemiga — the map was taken by Black Phoenix.
Dust2prediction missed13:8
Nemiga 48%Black Phoenix 52%
The model gave 52% on Black Phoenix — the map was taken by Nemiga.
Mirageprediction correct19:15
Nemiga 77%Black Phoenix 23%
The model gave 77% on Nemiga — the map was taken by Nemiga.
Model check result
Model favoriteNemiga · 76%
Series resultNemiga 2:1
Series predictioncorrect
Accuracy by map1 of 3