HyperX Retake Season 12 · BO3
result vs prediction
LP#107 in the world · win 2:0series probability
67%33%
probability at match start · final 2:0
BERG#192 in the world · loss 0:2The 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.
AncientLP pick
65%50%
LP · 13 mapsedge LP +15%BERG · 12 maps
Nukepossible decider
43%33%
LP · 10 mapsedge LP +10%BERG · 11 maps
InfernoBERG pick
50%50%
LP · 12 mapsnearly even +0%BERG · 6 maps
MirageLP ban
18%42%
LP · 7 mapsedge BERG +24%BERG · 8 maps
Dust2BERG ban
42%40%
LP · 8 mapsnearly even +2%BERG · 1 map
CacheBERG ban
73%60%
LP · 7 mapsedge LP +13%BERG · 1 map
AnubisLP ban
50%38%
LP · 0 mapsedge LP +12%BERG · 4 maps
Most likely veto scenario
1. BanLP remove Mirage
2. BanBERG remove Dust2
3. PickLP take Ancient
4. PickBERG take Inferno
5. BanBERG remove Cache
6. BanLP remove Anubis
DeciderNuke (43% / 33%)
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.
Nukeprediction correct13:5
LP 63%BERG 37%
The model gave 63% on LP — the map was taken by LP.
Mirageprediction missed13:8
LP 22%BERG 78%
The model gave 78% on BERG — the map was taken by LP.
Model check result
Model favoriteLP · 67%
Series resultLP 2:0
Series predictioncorrect
Accuracy by map1 of 2