ESL Challenger League Season 52 South America Cup 2 · BO3
result vs prediction
Turma do Pagode#91 in the world · win 2:0series probability
73%27%
probability at match start · final 2:0
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.
AncientTurma do Pagode pick
63%31%
Turma do Pagode · 12 mapsedge Turma do Pagode +32%MEIA NOITE · 9 maps
Dust2possible decider
50%50%
Turma do Pagode · 10 mapsnearly even +0%MEIA NOITE · 6 maps
MirageTurma do Pagode ban
50%38%
Turma do Pagode · 2 mapsedge Turma do Pagode +12%MEIA NOITE · 9 maps
InfernoMEIA NOITE ban
50%57%
Turma do Pagode · 4 mapsedge MEIA NOITE +7%MEIA NOITE · 3 maps
CacheMEIA NOITE ban
60%33%
Turma do Pagode · 1 mapedge Turma do Pagode +27%MEIA NOITE · 5 maps
DefaultMEIA NOITE pick
40%75%
Turma do Pagode · 1 mapedge MEIA NOITE +35%MEIA NOITE · 4 maps
NukeTurma do Pagode ban
33%43%
Turma do Pagode · 2 mapsedge MEIA NOITE +10%MEIA NOITE · 3 maps
Most likely veto scenario
1. BanTurma do Pagode remove Mirage
2. BanMEIA NOITE remove Cache
3. PickTurma do Pagode take Ancient
4. PickMEIA NOITE take Default
5. BanMEIA NOITE remove Inferno
6. BanTurma do Pagode remove Nuke
DeciderDust2 (50% / 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.
Nukeprediction missed13:11
Turma do Pagode 37%MEIA NOITE 63%
The model gave 63% on MEIA NOITE — the map was taken by Turma do Pagode.
Dust2prediction correct13:11
Turma do Pagode 53%MEIA NOITE 47%
The model gave 53% on Turma do Pagode — the map was taken by Turma do Pagode.
Model check result
Model favoriteTurma do Pagode · 73%
Series resultTurma do Pagode 2:0
Series predictioncorrect
Accuracy by map1 of 2