European Pro League Cup 5 · BO3
result vs predictionseries probability
38%62%
probability at match start · final 2:1
ALGO#146 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.
AnubisALGO pick
50%44%
Kinoa · 0 mapsedge Kinoa +6%ALGO · 5 maps
Nukepossible decider
50%50%
Kinoa · 0 mapsnearly even +0%ALGO · 4 maps
OverpassALGO ban
40%33%
Kinoa · 1 mapedge Kinoa +7%ALGO · 2 maps
InfernoKinoa ban
50%50%
Kinoa · 0 mapsnearly even +0%ALGO · 2 maps
MirageALGO ban
50%33%
Kinoa · 0 mapsedge Kinoa +17%ALGO · 2 maps
AncientKinoa ban
50%60%
Kinoa · 0 mapsedge ALGO +10%ALGO · 1 map
DefaultKinoa pick
50%40%
Kinoa · 0 mapsedge Kinoa +10%ALGO · 1 map
Most likely veto scenario
1. BanKinoa remove Inferno
2. BanALGO remove Mirage
3. PickKinoa take Default
4. PickALGO take Anubis
5. BanALGO remove Overpass
6. BanKinoa remove Ancient
DeciderNuke (50% / 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.
Infernoprediction correct1:13
Kinoa 47%ALGO 53%
The model gave 53% on ALGO — the map was taken by ALGO.
Mirageprediction correct13:7
Kinoa 69%ALGO 31%
The model gave 69% on Kinoa — the map was taken by Kinoa.
Ancientprediction missed13:10
Kinoa 40%ALGO 60%
The model gave 60% on ALGO — the map was taken by Kinoa.
Model check result
Model favoriteALGO · 62%
Series resultKinoa 2:1
Series predictionmissed
Accuracy by map2 of 3