European Pro League Series 9 · BO3
result vs prediction
Misa#115 in the world · loss 0:2series probability
63%37%
probability at match start · final 0:2
Leo#89 in the world · win 2:0The 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.
Dust2possible decider
49%43%
Misa · 31 mapedge Misa +6%Leo · 24 maps
AnubisMisa pick
53%38%
Misa · 28 mapsedge Misa +15%Leo · 9 maps
NukeLeo pick
48%83%
Misa · 17 mapsedge Leo +35%Leo · 20 maps
CacheMisa ban
45%43%
Misa · 25 mapsnearly even +2%Leo · 10 maps
MirageLeo ban
42%36%
Misa · 22 mapsedge Misa +6%Leo · 10 maps
AncientMisa ban
43%45%
Misa · 3 mapsnearly even -2%Leo · 18 maps
InfernoLeo ban
56%50%
Misa · 14 mapsedge Misa +6%Leo · 0 maps
Most likely veto scenario
1. BanMisa remove Ancient
2. BanLeo remove Inferno
3. PickMisa take Anubis
4. PickLeo take Nuke
5. BanLeo remove Mirage
6. BanMisa remove Cache
DeciderDust2 (49% / 43%)
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 correct6:13
Misa 14%Leo 86%
The model gave 86% on Leo — the map was taken by Leo.
Cacheprediction missed0:13
Misa 55%Leo 45%
The model gave 55% on Misa — the map was taken by Leo.
Model check result
Model favoriteMisa · 63%
Series resultLeo 0:2
Series predictionmissed
Accuracy by map1 of 2