European Pro League Series 7 · BO3
result vs prediction
G2 Ares#103 in the world · win 2:1series probability
51%49%
probability at match start · final 2:1
Young Ninjas#103 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.
Dust2Young Ninjas pick
50%40%
G2 Ares · 6 mapsedge G2 Ares +10%Young Ninjas · 11 maps
MirageYoung Ninjas ban
54%33%
G2 Ares · 9 mapsedge G2 Ares +21%Young Ninjas · 5 maps
AncientG2 Ares ban
55%60%
G2 Ares · 7 mapsedge Young Ninjas +5%Young Ninjas · 6 maps
OverpassG2 Ares pick
60%63%
G2 Ares · 6 mapsnearly even -3%Young Ninjas · 4 maps
Anubispossible decider
67%55%
G2 Ares · 2 mapsedge G2 Ares +12%Young Ninjas · 7 maps
InfernoYoung Ninjas ban
62%50%
G2 Ares · 9 mapsedge G2 Ares +12%Young Ninjas · 0 maps
NukeG2 Ares ban
50%75%
G2 Ares · 0 mapsedge Young Ninjas +25%Young Ninjas · 8 maps
Most likely veto scenario
1. BanG2 Ares remove Nuke
2. BanYoung Ninjas remove Inferno
3. PickG2 Ares take Overpass
4. PickYoung Ninjas take Dust2
5. BanYoung Ninjas remove Mirage
6. BanG2 Ares remove Ancient
DeciderAnubis (67% / 55%)
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 missed8:13
G2 Ares 50%Young Ninjas 50%
The model gave 50% on G2 Ares — the map was taken by Young Ninjas.
Dust2prediction correct13:11
G2 Ares 57%Young Ninjas 43%
The model gave 57% on G2 Ares — the map was taken by G2 Ares.
Mirageprediction correct13:2
G2 Ares 70%Young Ninjas 30%
The model gave 70% on G2 Ares — the map was taken by G2 Ares.
Model check result
Model favoriteG2 Ares · 51%
Series resultG2 Ares 2:1
Series predictioncorrect
Accuracy by map2 of 3