ESL Pro League Season 24 · BO3
result vs prediction
G2#7 in the world · loss 1:2series probability
78%22%
probability at match start · final 1:2
PARIVISION#20 in the world · win 2:1The 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.
AncientPARIVISION pick
61%67%
G2 · 14 mapsedge PARIVISION +6%PARIVISION · 8 maps
InfernoG2 pick
64%36%
G2 · 10 mapsedge G2 +28%PARIVISION · 7 maps
Dust2PARIVISION ban
38%40%
G2 · 9 mapsnearly even -2%PARIVISION · 6 maps
MiragePARIVISION ban
54%43%
G2 · 9 mapsedge G2 +11%PARIVISION · 3 maps
AnubisG2 ban
50%50%
G2 · 6 mapsnearly even +0%PARIVISION · 2 maps
CacheG2 ban
38%29%
G2 · 4 mapsedge G2 +9%PARIVISION · 3 maps
Most likely veto scenario
1. BanG2 remove Cache
2. BanPARIVISION remove Mirage
3. PickG2 take Inferno
4. PickPARIVISION take Ancient
5. BanPARIVISION remove Dust2
6. BanG2 remove Anubis
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.
Ancientprediction correct7:13
G2 41%PARIVISION 59%
The model gave 59% on PARIVISION — the map was taken by PARIVISION.
Anubisprediction correct13:9
G2 53%PARIVISION 47%
The model gave 53% on G2 — the map was taken by G2.
Infernoprediction missed11:13
G2 76%PARIVISION 24%
The model gave 76% on G2 — the map was taken by PARIVISION.
Model check result
Model favoriteG2 · 78%
Series resultPARIVISION 1:2
Series predictionmissed
Accuracy by map2 of 3