ESL Pro League Season 24 · BO3
result vs prediction
Aurora#6 in the world · win 2:0series probability
13%87%
probability at match start · final 2:0
Spirit#1 in the world · loss 0:2The 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.
Miragepossible decider
58%53%
Aurora · 15 mapsedge Aurora +5%Spirit · 11 maps
Dust2Spirit pick
50%65%
Aurora · 8 mapsedge Spirit +15%Spirit · 16 maps
AnubisAurora pick
67%75%
Aurora · 11 mapsedge Spirit +8%Spirit · 8 maps
CacheAurora ban
45%54%
Aurora · 7 mapsedge Spirit +9%Spirit · 9 maps
NukeSpirit ban
75%55%
Aurora · 8 mapsedge Aurora +20%Spirit · 7 maps
AncientAurora ban
40%79%
Aurora · 1 mapedge Spirit +39%Spirit · 10 maps
InfernoSpirit ban
55%50%
Aurora · 7 mapsedge Aurora +5%Spirit · 0 maps
Most likely veto scenario
1. BanAurora remove Ancient
2. BanSpirit remove Inferno
3. PickAurora take Anubis
4. PickSpirit take Dust2
5. BanSpirit remove Nuke
6. BanAurora remove Cache
DeciderMirage (58% / 53%)
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 correct13:9
Aurora 52%Spirit 48%
The model gave 52% on Aurora — the map was taken by Aurora.
Anubisprediction missed13:6
Aurora 43%Spirit 57%
The model gave 57% on Spirit — the map was taken by Aurora.
Model check result
Model favoriteSpirit · 87%
Series resultAurora 2:0
Series predictionmissed
Accuracy by map1 of 2