FRAG 20 · BO3
result vs prediction
LAG#95 in the world · win 2:1series probability
58%42%
probability at match start · final 2:1
EMPIRE#172 in the world · loss 1:2The 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.
AncientLAG pick
40%50%
LAG · 1 mapedge EMPIRE +10%EMPIRE · 0 maps
Dust2EMPIRE ban
50%60%
LAG · 0 mapsedge EMPIRE +10%EMPIRE · 1 map
InfernoEMPIRE ban
40%50%
LAG · 1 mapedge EMPIRE +10%EMPIRE · 0 maps
NukeEMPIRE pick
50%40%
LAG · 0 mapsedge LAG +10%EMPIRE · 1 map
OverpassLAG ban
50%60%
LAG · 0 mapsedge EMPIRE +10%EMPIRE · 1 map
Most likely veto scenario
1. BanLAG remove Overpass
2. BanEMPIRE remove Inferno
3. PickLAG take Ancient
4. PickEMPIRE take Nuke
5. BanEMPIRE 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.
Mirageprediction missed13:9
LAG 47%EMPIRE 53%
The model gave 53% on EMPIRE — the map was taken by LAG.
Infernoprediction correct11:13
LAG 43%EMPIRE 57%
The model gave 57% on EMPIRE — the map was taken by EMPIRE.
Nukeprediction correct13:10
LAG 60%EMPIRE 40%
The model gave 60% on LAG — the map was taken by LAG.
Model check result
Model favoriteLAG · 58%
Series resultLAG 2:1
Series predictioncorrect
Accuracy by map2 of 3