NSTLGA League Season 2 · BO1
result vs prediction
regain#162 in the world · loss 6:13series probability
55%45%
probability at match start · final 6:13
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.
MirageWithout a Roof ban
50%40%
regain · 8 mapsedge regain +10%Without a Roof · 1 map
Infernoregain ban
44%50%
regain · 5 mapsedge Without a Roof +6%Without a Roof · 2 maps
Ancientregain ban
44%40%
regain · 5 mapsnearly even +4%Without a Roof · 1 map
Dust2possible decider
56%60%
regain · 5 mapsnearly even -4%Without a Roof · 1 map
AnubisWithout a Roof ban
60%50%
regain · 1 mapedge regain +10%Without a Roof · 0 maps
CacheWithout a Roof ban
60%50%
regain · 1 mapedge regain +10%Without a Roof · 0 maps
Nukeregain ban
50%40%
regain · 0 mapsedge regain +10%Without a Roof · 1 map
Most likely veto scenario
1. Banregain remove Nuke
2. BanWithout a Roof remove Anubis
3. Banregain remove Ancient
4. BanWithout a Roof remove Mirage
5. Banregain remove Inferno
6. BanWithout a Roof remove Cache
DeciderDust2 (56% / 60%)
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 missed6:13
regain 60%Without a Roof 40%
The model gave 60% on regain — the map was taken by Without a Roof.
Model check result
Model favoriteregain · 55%
Series resultWithout a Roof 6:13
Series predictionmissed
Accuracy by map0 of 1