Exort Fiesta Series 2 · BO3
result vs prediction
Phantom Academy#182 in the world · win 2:1series probability
57%43%
probability at match start · final 2:1
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.
MirageKAMUI ban
77%50%
Phantom Academy · 9 mapsedge Phantom Academy +27%KAMUI · 0 maps
CacheKAMUI pick
30%50%
Phantom Academy · 6 mapsedge KAMUI +20%KAMUI · 0 maps
AncientPhantom Academy ban
44%50%
Phantom Academy · 5 mapsedge KAMUI +6%KAMUI · 0 maps
NukePhantom Academy pick
56%50%
Phantom Academy · 5 mapsedge Phantom Academy +6%KAMUI · 0 maps
Defaultpossible decider
43%50%
Phantom Academy · 3 mapsedge KAMUI +7%KAMUI · 0 maps
AnubisPhantom Academy ban
50%50%
Phantom Academy · 2 mapsnearly even +0%KAMUI · 0 maps
Dust2KAMUI ban
50%50%
Phantom Academy · 2 mapsnearly even +0%KAMUI · 0 maps
Most likely veto scenario
1. BanPhantom Academy remove Anubis
2. BanKAMUI remove Mirage
3. PickPhantom Academy take Nuke
4. PickKAMUI take Cache
5. BanKAMUI remove Dust2
6. BanPhantom Academy remove Ancient
DeciderDefault (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 missed7:13
Phantom Academy 79%KAMUI 21%
The model gave 79% on Phantom Academy — the map was taken by KAMUI.
Ancientprediction missed13:11
Phantom Academy 42%KAMUI 58%
The model gave 58% on KAMUI — the map was taken by Phantom Academy.
Dust2prediction correct16:12
Phantom Academy 50%KAMUI 50%
The model gave 50% on Phantom Academy — the map was taken by Phantom Academy.
Model check result
Model favoritePhantom Academy · 57%
Series resultPhantom Academy 2:1
Series predictioncorrect
Accuracy by map1 of 3