Roman Imperium Cup IX · BO3
result vs prediction
EAC#76 in the world · loss 0:2series probability
61%39%
probability at match start · final 0:2
PURE#126 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.
MirageEAC pick
52%36%
EAC · 27 mapsedge EAC +16%PURE · 7 maps
AncientEAC ban
59%63%
EAC · 18 mapsnearly even -4%PURE · 4 maps
Nukepossible decider
53%56%
EAC · 13 mapsnearly even -3%PURE · 5 maps
AnubisPURE ban
45%50%
EAC · 16 mapsedge PURE +5%PURE · 0 maps
InfernoEAC ban
33%67%
EAC · 11 mapsedge PURE +34%PURE · 5 maps
CachePURE ban
63%57%
EAC · 12 mapsedge EAC +6%PURE · 3 maps
DefaultPURE pick
50%50%
EAC · 4 mapsnearly even +0%PURE · 0 maps
Most likely veto scenario
1. BanEAC remove Inferno
2. BanPURE remove Anubis
3. PickEAC take Mirage
4. PickPURE take Default
5. BanPURE remove Cache
6. BanEAC remove Ancient
DeciderNuke (53% / 56%)
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.
Infernoprediction correct8:13
EAC 18%PURE 82%
The model gave 82% on PURE — the map was taken by PURE.
Anubisprediction correct4:13
EAC 48%PURE 52%
The model gave 52% on PURE — the map was taken by PURE.
Model check result
Model favoriteEAC · 61%
Series resultPURE 0:2
Series predictionmissed
Accuracy by map2 of 2