HyperX Retake Season 13 · BO3
result vs prediction
Metizport#65 in the world · win 1:0series probability
34%66%
probability at match start · final 1:0
TYLOO#32 in the world · loss 0:1The 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.
NukeMetizport pick
52%30%
Metizport · 25 mapsedge Metizport +22%TYLOO · 6 maps
MirageTYLOO pick
58%59%
Metizport · 15 mapsnearly even -1%TYLOO · 13 maps
Infernopossible decider
58%46%
Metizport · 15 mapsedge Metizport +12%TYLOO · 9 maps
AncientTYLOO ban
69%50%
Metizport · 12 mapsedge Metizport +19%TYLOO · 8 maps
CacheMetizport ban
57%63%
Metizport · 10 mapsedge TYLOO +6%TYLOO · 4 maps
AnubisTYLOO ban
62%38%
Metizport · 9 mapsedge Metizport +24%TYLOO · 4 maps
DefaultMetizport ban
50%67%
Metizport · 0 mapsedge TYLOO +17%TYLOO · 2 maps
Most likely veto scenario
1. BanMetizport remove Default
2. BanTYLOO remove Ancient
3. PickMetizport take Nuke
4. PickTYLOO take Mirage
5. BanTYLOO remove Anubis
6. BanMetizport remove Cache
DeciderInferno (58% / 46%)
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.
Defaultprediction missed1:0
Metizport 33%TYLOO 67%
The model gave 67% on TYLOO — the map was taken by Metizport.
Model check result
Model favoriteTYLOO · 66%
Series resultMetizport 1:0
Series predictionmissed
Accuracy by map0 of 1