FISSURE Playground 3 · BO3
result vs prediction
9z#13 in the world · loss 0:2series probability
74%26%
probability at match start · final 0:2
MIBR#28 in the world · win 2:0The 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.
Nukepossible decider
50%58%
9z · 8 mapsedge MIBR +8%MIBR · 8 maps
InfernoMIBR pick
50%64%
9z · 8 mapsedge MIBR +14%MIBR · 7 maps
Mirage9z ban
55%55%
9z · 7 mapsnearly even +0%MIBR · 7 maps
Dust2MIBR ban
50%50%
9z · 12 mapsnearly even +0%MIBR · 0 maps
Ancient9z ban
43%36%
9z · 3 mapsedge 9z +7%MIBR · 7 maps
CacheMIBR ban
57%63%
9z · 3 mapsedge MIBR +6%MIBR · 4 maps
Overpass9z pick
63%50%
9z · 4 mapsedge 9z +13%MIBR · 0 maps
Most likely veto scenario
1. Ban9z remove Ancient
2. BanMIBR remove Dust2
3. Pick9z take Overpass
4. PickMIBR take Inferno
5. BanMIBR remove Cache
6. Ban9z remove Mirage
DeciderNuke (50% / 58%)
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 correct6:13
9z 47%MIBR 53%
The model gave 53% on MIBR — the map was taken by MIBR.
Nukeprediction correct7:13
9z 45%MIBR 55%
The model gave 55% on MIBR — the map was taken by MIBR.
Model check result
Model favorite9z · 74%
Series resultMIBR 0:2
Series predictionmissed
Accuracy by map2 of 2