?
WINLINE MPKBK CIS LAN Season 9 · BO3
result vs prediction
WW#125 in the world · win 2:0
series probability
63%37%
probability at match start · final 2:0
WISPloss 0:2
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.
Dust2WW pick
50%40%
WW · 20 mapsedge WW +10%WISP · 1 map
MirageWISP ban
50%50%
WW · 14 mapsnearly even +0%WISP · 0 maps
AncientWW ban
40%60%
WW · 6 mapsedge WISP +20%WISP · 1 map
AnubisWISP ban
55%50%
WW · 7 mapsedge WW +5%WISP · 0 maps
CacheWISP pick
44%50%
WW · 5 mapsedge WISP +6%WISP · 2 maps
Nukepossible decider
56%50%
WW · 5 mapsedge WW +6%WISP · 0 maps
InfernoWW ban
60%50%
WW · 1 mapedge WW +10%WISP · 0 maps
Most likely veto scenario
1. BanWW remove Ancient
2. BanWISP remove Anubis
3. PickWW take Dust2
4. PickWISP take Cache
5. BanWISP remove Mirage
6. BanWW remove Inferno
DeciderNuke (56% / 50%)
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.
Infernoprediction correct13:6
WW 57%WISP 43%
The model gave 57% on WW — the map was taken by WW.
Dust2prediction correct13:1
WW 63%WISP 37%
The model gave 63% on WW — the map was taken by WW.
Model check result
Model favoriteWW · 63%
Series resultWW 2:0
Series predictioncorrect
Accuracy by map2 of 2