?
European Pro League Series 7 · BO3
result vs prediction
aAa#132 in the world · win 2:1
series probability
37%63%
probability at match start · final 2:1
RUSTEC#124 in the world · loss 1:2
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.
Dust2aAa pick
27%38%
aAa · 11 mapsedge RUSTEC +11%RUSTEC · 9 maps
Nukepossible decider
25%44%
aAa · 8 mapsedge RUSTEC +19%RUSTEC · 5 maps
InfernoRUSTEC pick
27%71%
aAa · 7 mapsedge RUSTEC +44%RUSTEC · 3 maps
OverpassaAa ban
29%38%
aAa · 3 mapsedge RUSTEC +9%RUSTEC · 4 maps
AncientRUSTEC ban
20%50%
aAa · 6 mapsedge RUSTEC +30%RUSTEC · 0 maps
MirageaAa ban
50%56%
aAa · 0 mapsedge RUSTEC +6%RUSTEC · 5 maps
AnubisRUSTEC ban
60%40%
aAa · 1 mapedge aAa +20%RUSTEC · 1 map
Most likely veto scenario
1. BanaAa remove Mirage
2. BanRUSTEC remove Anubis
3. PickaAa take Dust2
4. PickRUSTEC take Inferno
5. BanRUSTEC remove Ancient
6. BanaAa remove Overpass
DeciderNuke (25% / 44%)
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 correct7:13
aAa 37%RUSTEC 63%
The model gave 63% on RUSTEC — the map was taken by RUSTEC.
Dust2prediction missed16:13
aAa 40%RUSTEC 60%
The model gave 60% on RUSTEC — the map was taken by aAa.
Nukeprediction missed13:8
aAa 29%RUSTEC 71%
The model gave 71% on RUSTEC — the map was taken by aAa.
Model check result
Model favoriteRUSTEC · 63%
Series resultaAa 2:1
Series predictionmissed
Accuracy by map1 of 3