NSTLGA League Season 1 · BO3
result vs prediction
Marsborne#82 in the world · win 2:0series probability
69%31%
probability at match start · final 2:0
F5#208 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.
AncientF5 pick
56%50%
Marsborne · 5 mapsedge Marsborne +6%F5 · 6 maps
InfernoMarsborne pick
70%50%
Marsborne · 6 mapsedge Marsborne +20%F5 · 4 maps
Miragepossible decider
60%67%
Marsborne · 6 mapsedge F5 +7%F5 · 2 maps
AnubisF5 ban
57%43%
Marsborne · 3 mapsedge Marsborne +14%F5 · 3 maps
OverpassMarsborne ban
57%50%
Marsborne · 3 mapsedge Marsborne +7%F5 · 2 maps
NukeMarsborne ban
50%43%
Marsborne · 0 mapsedge Marsborne +7%F5 · 3 maps
DefaultF5 ban
40%50%
Marsborne · 1 mapedge F5 +10%F5 · 0 maps
Most likely veto scenario
1. BanMarsborne remove Nuke
2. BanF5 remove Default
3. PickMarsborne take Inferno
4. PickF5 take Ancient
5. BanF5 remove Anubis
6. BanMarsborne remove Overpass
DeciderMirage (60% / 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.
Overpassprediction correct13:3
Marsborne 54%F5 46%
The model gave 54% on Marsborne — the map was taken by Marsborne.
Infernoprediction correct13:4
Marsborne 72%F5 28%
The model gave 72% on Marsborne — the map was taken by Marsborne.
Model check result
Model favoriteMarsborne · 69%
Series resultMarsborne 2:0
Series predictioncorrect
Accuracy by map2 of 2