FERJEE In House Season 2 · BO5
result vs prediction
Imperial#51 in the world · win 3:0series probability
41%59%
probability at match start · final 3:0
paiN#29 in the world · loss 0:3The 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.
InfernoImperial pick
66%36%
Imperial · 25 mapsedge Imperial +30%paiN · 10 maps
MirageImperial pick
71%50%
Imperial · 24 mapsedge Imperial +21%paiN · 8 maps
NukepaiN pick
71%47%
Imperial · 20 mapsedge Imperial +24%paiN · 11 maps
Dust2Imperial ban
56%67%
Imperial · 14 mapsedge paiN +11%paiN · 11 maps
CachepaiN ban
65%33%
Imperial · 13 mapsedge Imperial +32%paiN · 8 maps
AnubispaiN pick
58%50%
Imperial · 8 mapsedge Imperial +8%paiN · 4 maps
Most likely veto scenario
1. BanImperial remove Dust2
2. BanpaiN remove Cache
3. PickImperial take Mirage
4. PickpaiN take Nuke
5. PickImperial take Inferno
6. PickpaiN take Anubis
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.
Anubisprediction correct13:4
Imperial 55%paiN 45%
The model gave 55% on Imperial — the map was taken by Imperial.
Cacheprediction correct13:11
Imperial 81%paiN 19%
The model gave 81% on Imperial — the map was taken by Imperial.
Mirageprediction correct13:6
Imperial 69%paiN 31%
The model gave 69% on Imperial — the map was taken by Imperial.
Model check result
Model favoritepaiN · 59%
Series resultImperial 3:0
Series predictionmissed
Accuracy by map3 of 3