ESL Pro League Season 24 · BO3
result vs prediction
Spirit#1 in the world · win 2:1series probability
97%3%
probability at match start · final 2:1
ShindeN#77 in the world · loss 1:2The 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.
Dust2Spirit pick
73%62%
Spirit · 11 mapsedge Spirit +11%ShindeN · 9 maps
MirageSpirit ban
45%36%
Spirit · 7 mapsedge Spirit +9%ShindeN · 10 maps
NukeShindeN pick
56%60%
Spirit · 5 mapsnearly even -4%ShindeN · 11 maps
Ancientpossible decider
85%56%
Spirit · 9 mapsedge Spirit +29%ShindeN · 5 maps
CacheShindeN ban
55%36%
Spirit · 7 mapsedge Spirit +19%ShindeN · 7 maps
InfernoSpirit ban
50%53%
Spirit · 0 mapsnearly even -3%ShindeN · 13 maps
AnubisShindeN ban
78%50%
Spirit · 5 mapsedge Spirit +28%ShindeN · 0 maps
Most likely veto scenario
1. BanSpirit remove Inferno
2. BanShindeN remove Anubis
3. PickSpirit take Dust2
4. PickShindeN take Nuke
5. BanShindeN remove Cache
6. BanSpirit remove Mirage
DeciderAncient (85% / 56%)
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.
Dust2prediction missed11:13
Spirit 66%ShindeN 34%
The model gave 66% on Spirit — the map was taken by ShindeN.
Nukeprediction missed13:11
Spirit 42%ShindeN 58%
The model gave 58% on ShindeN — the map was taken by Spirit.
Mirageprediction correct13:4
Spirit 60%ShindeN 40%
The model gave 60% on Spirit — the map was taken by Spirit.
Model check result
Model favoriteSpirit · 97%
Series resultSpirit 2:1
Series predictioncorrect
Accuracy by map1 of 3