European Pro League Series 9 · BO5
result vs prediction
Leo#89 in the world · loss 1:3series probability
53%47%
probability at match start · final 1:3
mellren#94 in the world · win 3:1The 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.
Dust2Leo pick
41%58%
Leo · 23 mapsedge mellren +17%mellren · 8 maps
Nukemellren ban
85%25%
Leo · 23 mapsedge Leo +60%mellren · 8 maps
Miragemellren pick
38%68%
Leo · 9 mapsedge mellren +30%mellren · 21 map
Ancientmellren pick
40%69%
Leo · 16 mapsedge mellren +29%mellren · 12 maps
Anubispossible decider
36%67%
Leo · 10 mapsedge mellren +31%mellren · 5 maps
CacheLeo pick
47%50%
Leo · 13 mapsnearly even -3%mellren · 0 maps
InfernoLeo ban
50%59%
Leo · 0 mapsedge mellren +9%mellren · 13 maps
Most likely veto scenario
1. BanLeo remove Inferno
2. Banmellren remove Nuke
3. PickLeo take Cache
4. Pickmellren take Mirage
5. PickLeo take Dust2
6. Pickmellren take Ancient
DeciderAnubis (36% / 67%)
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 correct13:10
Leo 95%mellren 5%
The model gave 95% on Leo — the map was taken by Leo.
Mirageprediction correct11:13
Leo 21%mellren 79%
The model gave 79% on mellren — the map was taken by mellren.
Dust2prediction correct8:13
Leo 36%mellren 64%
The model gave 64% on mellren — the map was taken by mellren.
Ancientprediction correct1:13
Leo 21%mellren 79%
The model gave 79% on mellren — the map was taken by mellren.
Model check result
Model favoriteLeo · 53%
Series resultmellren 1:3
Series predictionmissed
Accuracy by map4 of 4