?
ESL Challenger League Season 52 North America Cup 2 · BO3
result vs prediction
Marsborne#82 in the world · win 2:0
series probability
74%26%
probability at match start · final 2:0
Iowa Stormboar#162 in the world · loss 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
61%71%
Marsborne · 14 mapsedge Iowa Stormboar +10%Iowa Stormboar · 3 maps
InfernoIowa Stormboar ban
60%30%
Marsborne · 11 mapsedge Marsborne +30%Iowa Stormboar · 6 maps
MirageIowa Stormboar pick
67%62%
Marsborne · 8 mapsedge Marsborne +5%Iowa Stormboar · 9 maps
Dust2Marsborne ban
58%70%
Marsborne · 8 mapsedge Iowa Stormboar +12%Iowa Stormboar · 6 maps
Nukepossible decider
50%30%
Marsborne · 6 mapsedge Marsborne +20%Iowa Stormboar · 6 maps
AnubisIowa Stormboar ban
67%33%
Marsborne · 5 mapsedge Marsborne +34%Iowa Stormboar · 2 maps
CacheMarsborne ban
40%50%
Marsborne · 1 mapedge Iowa Stormboar +10%Iowa Stormboar · 4 maps
Most likely veto scenario
1. BanMarsborne remove Cache
2. BanIowa Stormboar remove Inferno
3. PickMarsborne take Ancient
4. PickIowa Stormboar take Mirage
5. BanIowa Stormboar remove Anubis
6. BanMarsborne remove Dust2
DeciderNuke (50% / 30%)
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 missed13:2
Marsborne 36%Iowa Stormboar 64%
The model gave 64% on Iowa Stormboar — the map was taken by Marsborne.
Anubisprediction correct13:11
Marsborne 82%Iowa Stormboar 18%
The model gave 82% on Marsborne — the map was taken by Marsborne.
Model check result
Model favoriteMarsborne · 74%
Series resultMarsborne 2:0
Series predictioncorrect
Accuracy by map1 of 2