European Pro League Series 8 · BO3
result vs predictionseries probability
45%55%
probability at match start · final 1:2
1win#33 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.
MirageJust Players pick
52%38%
Just Players · 21 mapedge Just Players +14%1win · 9 maps
Ancientpossible decider
55%50%
Just Players · 16 mapsedge Just Players +5%1win · 4 maps
Dust21win pick
39%70%
Just Players · 14 mapsedge 1win +31%1win · 6 maps
Overpass1win ban
60%33%
Just Players · 6 mapsedge Just Players +27%1win · 5 maps
Nuke1win ban
50%50%
Just Players · 10 mapsnearly even +0%1win · 0 maps
AnubisJust Players ban
71%50%
Just Players · 3 mapsedge Just Players +21%1win · 4 maps
CacheJust Players ban
29%67%
Just Players · 3 mapsedge 1win +38%1win · 2 maps
Most likely veto scenario
1. BanJust Players remove Cache
2. Ban1win remove Nuke
3. PickJust Players take Mirage
4. Pick1win take Dust2
5. Ban1win remove Overpass
6. BanJust Players remove Anubis
DeciderAncient (55% / 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.
Mirageprediction correct13:6
Just Players 66%1win 34%
The model gave 66% on Just Players — the map was taken by Just Players.
Dust2prediction correct6:13
Just Players 19%1win 81%
The model gave 81% on 1win — the map was taken by 1win.
Ancientprediction missed7:13
Just Players 55%1win 45%
The model gave 55% on Just Players — the map was taken by 1win.
Model check result
Model favorite1win · 55%
Series result1win 1:2
Series predictioncorrect
Accuracy by map2 of 3