?
Roman Imperium Cup IX · BO1
result vs prediction
OG#203 in the world · loss 6:13
series probability
62%38%
probability at match start · final 6:13
PURE#126 in the world · win 13:6
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.
MirageOG ban
58%36%
OG · 8 mapsedge OG +22%PURE · 7 maps
Dust2PURE ban
73%57%
OG · 11 mapsedge OG +16%PURE · 3 maps
InfernoOG ban
27%63%
OG · 7 mapsedge PURE +36%PURE · 4 maps
Nukepossible decider
55%43%
OG · 7 mapsedge OG +12%PURE · 3 maps
AncientPURE ban
60%50%
OG · 6 mapsedge OG +10%PURE · 2 maps
CacheOG ban
33%57%
OG · 5 mapsedge PURE +24%PURE · 3 maps
Most likely veto scenario
1. BanOG remove Cache
2. BanPURE remove Dust2
3. BanOG remove Inferno
4. BanPURE remove Ancient
5. BanOG remove Mirage
DeciderNuke (55% / 43%)
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.
Nukeprediction missed6:13
OG 62%PURE 38%
The model gave 62% on OG — the map was taken by PURE.
Model check result
Model favoriteOG · 62%
Series resultPURE 6:13
Series predictionmissed
Accuracy by map0 of 1