?
Kibertochka Season 2 · BO3
result vs prediction
FORZE Reload#75 in the world · win 2:0
series probability
72%28%
probability at match start · final 2:0
DONSTU#221 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.
AnubisDONSTU pick
57%48%
FORZE Reload · 3 mapsedge FORZE Reload +9%DONSTU · 17 maps
Dust2FORZE Reload pick
67%39%
FORZE Reload · 5 mapsedge FORZE Reload +28%DONSTU · 14 maps
CacheFORZE Reload ban
57%46%
FORZE Reload · 3 mapsedge FORZE Reload +11%DONSTU · 9 maps
Ancientpossible decider
67%38%
FORZE Reload · 2 mapsedge FORZE Reload +29%DONSTU · 9 maps
NukeDONSTU ban
57%25%
FORZE Reload · 3 mapsedge FORZE Reload +32%DONSTU · 8 maps
InfernoFORZE Reload ban
50%50%
FORZE Reload · 0 mapsnearly even +0%DONSTU · 6 maps
MirageDONSTU ban
56%50%
FORZE Reload · 5 mapsedge FORZE Reload +6%DONSTU · 0 maps
Most likely veto scenario
1. BanFORZE Reload remove Inferno
2. BanDONSTU remove Mirage
3. PickFORZE Reload take Dust2
4. PickDONSTU take Anubis
5. BanDONSTU remove Nuke
6. BanFORZE Reload remove Cache
DeciderAncient (67% / 38%)
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 correct13:5
FORZE Reload 58%DONSTU 42%
The model gave 58% on FORZE Reload — the map was taken by FORZE Reload.
Cacheprediction correct13:8
FORZE Reload 58%DONSTU 42%
The model gave 58% on FORZE Reload — the map was taken by FORZE Reload.
Model check result
Model favoriteFORZE Reload · 72%
Series resultFORZE Reload 2:0
Series predictioncorrect
Accuracy by map2 of 2