NSTLGA League Season 2 · BO3
result vs prediction
LAG#95 in the world · win 2:1series probability
79%21%
probability at match start · final 2:1
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.
NukeFor Fun ban
44%50%
LAG · 5 mapsedge For Fun +6%For Fun · 4 maps
InfernoLAG ban
44%57%
LAG · 5 mapsedge For Fun +13%For Fun · 3 maps
Miragepossible decider
50%50%
LAG · 4 mapsnearly even +0%For Fun · 4 maps
AncientLAG ban
38%67%
LAG · 4 mapsedge For Fun +29%For Fun · 2 maps
Dust2For Fun ban
63%33%
LAG · 4 mapsedge LAG +30%For Fun · 2 maps
AnubisLAG pick
71%60%
LAG · 3 mapsedge LAG +11%For Fun · 1 map
DefaultFor Fun pick
50%50%
LAG · 2 mapsnearly even +0%For Fun · 0 maps
Most likely veto scenario
1. BanLAG remove Ancient
2. BanFor Fun remove Dust2
3. PickLAG take Anubis
4. PickFor Fun take Default
5. BanFor Fun remove Nuke
6. BanLAG remove Inferno
DeciderMirage (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 missed13:9
LAG 42%For Fun 58%
The model gave 58% on For Fun — the map was taken by LAG.
Dust2prediction missed10:13
LAG 79%For Fun 21%
The model gave 79% on LAG — the map was taken by For Fun.
Ancientprediction missed13:8
LAG 23%For Fun 77%
The model gave 77% on For Fun — the map was taken by LAG.
Model check result
Model favoriteLAG · 79%
Series resultLAG 2:1
Series predictioncorrect
Accuracy by map0 of 3