European Pro League Series 7 Closed Qualifier · BO3
result vs prediction
Young Ninjas#103 in the world · win 2:1series probability
56%44%
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.
Dust2Young Ninjas pick
44%23%
Young Ninjas · 5 mapsedge Young Ninjas +21%Lilmix · 9 maps
Miragepossible decider
40%40%
Young Ninjas · 1 mapnearly even +0%Lilmix · 11 maps
AncientLilmix ban
50%42%
Young Ninjas · 2 mapsedge Young Ninjas +8%Lilmix · 8 maps
OverpassLilmix pick
50%60%
Young Ninjas · 0 mapsedge Lilmix +10%Lilmix · 6 maps
InfernoYoung Ninjas ban
50%78%
Young Ninjas · 0 mapsedge Lilmix +28%Lilmix · 5 maps
AnubisLilmix ban
43%50%
Young Ninjas · 3 mapsedge Lilmix +7%Lilmix · 0 maps
DefaultYoung Ninjas ban
50%33%
Young Ninjas · 0 mapsedge Young Ninjas +17%Lilmix · 2 maps
Most likely veto scenario
1. BanYoung Ninjas remove Inferno
2. BanLilmix remove Anubis
3. PickYoung Ninjas take Dust2
4. PickLilmix take Overpass
5. BanLilmix remove Ancient
6. BanYoung Ninjas remove Default
DeciderMirage (40% / 40%)
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.
Overpassprediction missed13:6
Young Ninjas 37%Lilmix 63%
The model gave 63% on Lilmix — the map was taken by Young Ninjas.
Dust2prediction missed4:13
Young Ninjas 75%Lilmix 25%
The model gave 75% on Young Ninjas — the map was taken by Lilmix.
Ancientprediction correct13:7
Young Ninjas 58%Lilmix 42%
The model gave 58% on Young Ninjas — the map was taken by Young Ninjas.
Model check result
Model favoriteYoung Ninjas · 56%
Series resultYoung Ninjas 2:1
Series predictioncorrect
Accuracy by map1 of 3