FERJEE In House Season 2 · BO3
result vs prediction
Bounty Hunters#74 in the world · win 2:0series probability
79%21%
probability at match start · final 2:0
Keyd Stars#155 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.
Miragepossible decider
50%53%
Bounty Hunters · 18 mapsnearly even -3%Keyd Stars · 15 maps
AncientKeyd Stars pick
36%55%
Bounty Hunters · 10 mapsedge Keyd Stars +19%Keyd Stars · 18 maps
NukeBounty Hunters pick
56%33%
Bounty Hunters · 14 mapsedge Bounty Hunters +23%Keyd Stars · 8 maps
CacheKeyd Stars ban
58%40%
Bounty Hunters · 20 mapsedge Bounty Hunters +18%Keyd Stars · 1 map
Dust2Keyd Stars ban
42%42%
Bounty Hunters · 8 mapsnearly even +0%Keyd Stars · 8 maps
AnubisBounty Hunters ban
60%67%
Bounty Hunters · 6 mapsedge Keyd Stars +7%Keyd Stars · 5 maps
InfernoBounty Hunters ban
50%36%
Bounty Hunters · 0 mapsedge Bounty Hunters +14%Keyd Stars · 7 maps
Most likely veto scenario
1. BanBounty Hunters remove Inferno
2. BanKeyd Stars remove Cache
3. PickBounty Hunters take Nuke
4. PickKeyd Stars take Ancient
5. BanKeyd Stars remove Dust2
6. BanBounty Hunters remove Anubis
DeciderMirage (50% / 53%)
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.
Ancientprediction missed13:5
Bounty Hunters 29%Keyd Stars 71%
The model gave 71% on Keyd Stars — the map was taken by Bounty Hunters.
Mirageprediction correct13:7
Bounty Hunters 50%Keyd Stars 50%
The model gave 50% on Bounty Hunters — the map was taken by Bounty Hunters.
Model check result
Model favoriteBounty Hunters · 79%
Series resultBounty Hunters 2:0
Series predictioncorrect
Accuracy by map1 of 2