Exort Fiesta Series 2 · BO3
result vs prediction
STATE#137 in the world · win 2:1series probability
52%48%
probability at match start · final 2:1
KAMUI#187 in the world · loss 1:2The 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.
MirageKAMUI pick
33%78%
STATE · 2 mapsedge KAMUI +45%KAMUI · 5 maps
AncientSTATE ban
33%40%
STATE · 5 mapsedge KAMUI +7%KAMUI · 1 map
NukeKAMUI ban
50%50%
STATE · 6 mapsnearly even +0%KAMUI · 0 maps
CacheSTATE pick
50%60%
STATE · 4 mapsedge KAMUI +10%KAMUI · 1 map
Infernopossible decider
43%50%
STATE · 3 mapsedge KAMUI +7%KAMUI · 2 maps
Dust2STATE ban
50%57%
STATE · 0 mapsedge KAMUI +7%KAMUI · 3 maps
AnubisKAMUI ban
40%40%
STATE · 1 mapnearly even +0%KAMUI · 1 map
Most likely veto scenario
1. BanSTATE remove Dust2
2. BanKAMUI remove Nuke
3. PickSTATE take Cache
4. PickKAMUI take Mirage
5. BanKAMUI remove Anubis
6. BanSTATE remove Ancient
DeciderInferno (43% / 50%)
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.
Mirageprediction correct8:13
STATE 11%KAMUI 89%
The model gave 89% on KAMUI — the map was taken by KAMUI.
Cacheprediction missed13:7
STATE 43%KAMUI 57%
The model gave 57% on KAMUI — the map was taken by STATE.
Ancientprediction missed13:11
STATE 43%KAMUI 57%
The model gave 57% on KAMUI — the map was taken by STATE.
Model check result
Model favoriteSTATE · 52%
Series resultSTATE 2:1
Series predictioncorrect
Accuracy by map1 of 3