Roman Imperium Cup IX · BO1
result vs prediction
PURE#126 in the world · win 13:9series probability
63%37%
probability at match start · final 13:9
SINQU#217 in the world · loss 9:13The 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.
CacheSINQU ban
57%27%
PURE · 3 mapsedge PURE +30%SINQU · 7 maps
Nukepossible decider
50%60%
PURE · 4 mapsedge SINQU +10%SINQU · 6 maps
MiragePURE ban
36%50%
PURE · 7 mapsedge SINQU +14%SINQU · 0 maps
AncientPURE ban
50%25%
PURE · 2 mapsedge PURE +25%SINQU · 4 maps
InfernoSINQU ban
63%50%
PURE · 4 mapsedge PURE +13%SINQU · 2 maps
Dust2SINQU ban
57%40%
PURE · 3 mapsedge PURE +17%SINQU · 1 map
AnubisPURE ban
50%33%
PURE · 0 mapsedge PURE +17%SINQU · 2 maps
Most likely veto scenario
1. BanPURE remove Anubis
2. BanSINQU remove Dust2
3. BanPURE remove Mirage
4. BanSINQU remove Inferno
5. BanPURE remove Ancient
6. BanSINQU remove Cache
DeciderNuke (50% / 60%)
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 missed13:9
PURE 40%SINQU 60%
The model gave 60% on SINQU — the map was taken by PURE.
Model check result
Model favoritePURE · 63%
Series resultPURE 13:9
Series predictioncorrect
Accuracy by map0 of 1