Intel EPIC48 · BO3
result vs predictionseries probability
50%50%
probability at match start · final 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.
NukeVoracity pick
50%40%
Voracity · 2 mapsedge Voracity +10%Glitchtech UK · 1 map
AnubisGlitchtech UK pick
60%60%
Voracity · 1 mapnearly even +0%Glitchtech UK · 1 map
AncientGlitchtech UK ban
60%50%
Voracity · 1 mapedge Voracity +10%Glitchtech UK · 0 maps
Dust2Glitchtech UK ban
40%50%
Voracity · 1 mapedge Glitchtech UK +10%Glitchtech UK · 0 maps
MirageVoracity ban
50%60%
Voracity · 0 mapsedge Glitchtech UK +10%Glitchtech UK · 1 map
Most likely veto scenario
1. BanVoracity remove Mirage
2. BanGlitchtech UK remove Ancient
3. PickVoracity take Nuke
4. PickGlitchtech UK take Anubis
5. BanGlitchtech UK remove Dust2
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.
Dust2prediction correct14:16
Voracity 37%Glitchtech UK 63%
The model gave 63% on Glitchtech UK — the map was taken by Glitchtech UK.
Ancientprediction correct13:10
Voracity 63%Glitchtech UK 37%
The model gave 63% on Voracity — the map was taken by Voracity.
Anubisprediction missed6:13
Voracity 50%Glitchtech UK 50%
The model gave 50% on Voracity — the map was taken by Glitchtech UK.
Model check result
Model favoriteGlitchtech UK · 50%
Series resultGlitchtech UK 1:2
Series predictioncorrect
Accuracy by map2 of 3