Stake Ranked Episode 4 · BO3
result vs prediction
Alliance#22 in the world · loss 0:2series probability
62%38%
probability at match start · final 0:2
Nemiga#22 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.
AncientAlliance pick
64%57%
Alliance · 7 mapsedge Alliance +7%Nemiga · 24 maps
Dust2Nemiga ban
33%57%
Alliance · 5 mapsedge Nemiga +24%Nemiga · 19 maps
Nukepossible decider
50%67%
Alliance · 4 mapsedge Nemiga +17%Nemiga · 14 maps
MirageAlliance ban
50%76%
Alliance · 0 mapsedge Nemiga +26%Nemiga · 17 maps
AnubisNemiga pick
50%74%
Alliance · 0 mapsedge Nemiga +24%Nemiga · 15 maps
CacheAlliance ban
33%69%
Alliance · 2 mapsedge Nemiga +36%Nemiga · 12 maps
InfernoNemiga ban
60%60%
Alliance · 11 mapsnearly even +0%Nemiga · 1 map
Most likely veto scenario
1. BanAlliance remove Mirage
2. BanNemiga remove Inferno
3. PickAlliance take Ancient
4. PickNemiga take Anubis
5. BanNemiga remove Dust2
6. BanAlliance remove Cache
DeciderNuke (50% / 67%)
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 correct6:13
Alliance 17%Nemiga 83%
The model gave 83% on Nemiga — the map was taken by Nemiga.
Ancientprediction missed8:13
Alliance 60%Nemiga 40%
The model gave 60% on Alliance — the map was taken by Nemiga.
Model check result
Model favoriteAlliance · 62%
Series resultNemiga 0:2
Series predictionmissed
Accuracy by map1 of 2