FRAG 20 · BO3
result vs prediction
M80#30 in the world · loss 1:2series probability
90%10%
probability at match start · final 1:2
Marsborne#84 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.
AncientM80 ban
50%60%
M80 · 0 mapsedge Marsborne +10%Marsborne · 1 map
Dust2Marsborne ban
50%40%
M80 · 0 mapsedge M80 +10%Marsborne · 1 map
InfernoM80 pick
50%60%
M80 · 0 mapsedge Marsborne +10%Marsborne · 1 map
MirageMarsborne pick
50%60%
M80 · 0 mapsedge Marsborne +10%Marsborne · 1 map
OverpassMarsborne ban
50%60%
M80 · 0 mapsedge Marsborne +10%Marsborne · 1 map
Most likely veto scenario
1. BanM80 remove Ancient
2. BanMarsborne remove Dust2
3. PickM80 take Inferno
4. PickMarsborne take Mirage
5. BanMarsborne remove Overpass
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 missed13:5
M80 37%Marsborne 63%
The model gave 63% on Marsborne — the map was taken by M80.
Ancientprediction correct9:13
M80 43%Marsborne 57%
The model gave 57% on Marsborne — the map was taken by Marsborne.
Anubisprediction missed8:13
M80 50%Marsborne 50%
The model gave 50% on M80 — the map was taken by Marsborne.
Model check result
Model favoriteM80 · 90%
Series resultMarsborne 1:2
Series predictionmissed
Accuracy by map1 of 3