?
arrow_backBack to match
WINLINE MPKBK CIS LAN Season 7 · BO5
result vs prediction
Nemiga#22 in the world · win 3:1
series probability
62%38%
probability at match start · final 3:1
Nemesis#43 in the world · loss 1:3
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.
AncientNemesis pick
50%55%
Nemiga · 20 mapsedge Nemesis +5%Nemesis · 18 maps
Dust2possible decider
58%61%
Nemiga · 15 mapsnearly even -3%Nemesis · 14 maps
MirageNemiga pick
75%60%
Nemiga · 12 mapsedge Nemiga +15%Nemesis · 11 maps
NukeNemesis pick
63%64%
Nemiga · 12 mapsnearly even -1%Nemesis · 10 maps
AnubisNemesis ban
72%50%
Nemiga · 14 mapsedge Nemiga +22%Nemesis · 0 maps
CacheNemiga pick
67%60%
Nemiga · 8 mapsedge Nemiga +7%Nemesis · 6 maps
InfernoNemiga ban
60%50%
Nemiga · 1 mapedge Nemiga +10%Nemesis · 12 maps
Most likely veto scenario
1. BanNemiga remove Inferno
2. BanNemesis remove Anubis
3. PickNemiga take Mirage
4. PickNemesis take Nuke
5. PickNemiga take Cache
6. PickNemesis take Ancient
DeciderDust2 (58% / 61%)
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 correct13:6
Nemiga 69%Nemesis 31%
The model gave 69% on Nemiga — the map was taken by Nemiga.
Ancientprediction missed13:8
Nemiga 42%Nemesis 58%
The model gave 58% on Nemesis — the map was taken by Nemiga.
Cacheprediction missed17:19
Nemiga 60%Nemesis 40%
The model gave 60% on Nemiga — the map was taken by Nemesis.
Dust2prediction missed19:17
Nemiga 44%Nemesis 56%
The model gave 56% on Nemesis — the map was taken by Nemiga.
Model check result
Model favoriteNemiga · 62%
Series resultNemiga 3:1
Series predictioncorrect
Accuracy by map1 of 4