ESEA Season 58 North America Finals · BO3
result vs prediction
Marsborne#82 in the world · loss 0:2series probability
45%55%
probability at match start · final 0:2
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.
AncientMarsborne pick
63%50%
Marsborne · 15 mapsedge Marsborne +13%Without a Roof · 10 maps
Infernopossible decider
63%69%
Marsborne · 12 mapsedge Without a Roof +6%Without a Roof · 12 maps
MirageMarsborne ban
67%63%
Marsborne · 8 mapsnearly even +4%Without a Roof · 12 maps
Dust2Marsborne ban
58%40%
Marsborne · 8 mapsedge Marsborne +18%Without a Roof · 6 maps
NukeWithout a Roof ban
55%55%
Marsborne · 7 mapsnearly even +0%Without a Roof · 7 maps
AnubisWithout a Roof ban
70%60%
Marsborne · 6 mapsedge Marsborne +10%Without a Roof · 1 map
DefaultWithout a Roof pick
63%50%
Marsborne · 4 mapsedge Marsborne +13%Without a Roof · 0 maps
Most likely veto scenario
1. BanMarsborne remove Mirage
2. BanWithout a Roof remove Anubis
3. PickMarsborne take Ancient
4. PickWithout a Roof take Default
5. BanWithout a Roof remove Nuke
6. BanMarsborne remove Dust2
DeciderInferno (63% / 69%)
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 missed17:19
Marsborne 52%Without a Roof 48%
The model gave 52% on Marsborne — the map was taken by Without a Roof.
Nukeprediction missed9:13
Marsborne 53%Without a Roof 47%
The model gave 53% on Marsborne — the map was taken by Without a Roof.
Model check result
Model favoriteWithout a Roof · 55%
Series resultWithout a Roof 0:2
Series predictioncorrect
Accuracy by map0 of 2