?
NSTLGA League Season 2 · BO3
result vs prediction
Iowa Stormboar#162 in the world · loss 1:2
series probability
29%71%
probability at match start · final 1:2
LAG#91 in the world · win 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.
MirageLAG ban
57%50%
Iowa Stormboar · 10 mapsedge Iowa Stormboar +7%LAG · 6 maps
Nukepossible decider
50%55%
Iowa Stormboar · 8 mapsedge LAG +5%LAG · 7 maps
Dust2LAG pick
50%58%
Iowa Stormboar · 6 mapsedge LAG +8%LAG · 8 maps
InfernoIowa Stormboar ban
30%50%
Iowa Stormboar · 6 mapsedge LAG +20%LAG · 8 maps
AncientIowa Stormboar pick
78%50%
Iowa Stormboar · 5 mapsedge Iowa Stormboar +28%LAG · 6 maps
AnubisIowa Stormboar ban
50%71%
Iowa Stormboar · 2 mapsedge LAG +21%LAG · 3 maps
CacheLAG ban
50%50%
Iowa Stormboar · 2 mapsnearly even +0%LAG · 0 maps
Most likely veto scenario
1. BanIowa Stormboar remove Inferno
2. BanLAG remove Cache
3. PickIowa Stormboar take Ancient
4. PickLAG take Dust2
5. BanLAG remove Mirage
6. BanIowa Stormboar remove Anubis
DeciderNuke (50% / 55%)
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 correct13:7
Iowa Stormboar 60%LAG 40%
The model gave 60% on Iowa Stormboar — the map was taken by Iowa Stormboar.
Nukeprediction correct6:13
Iowa Stormboar 42%LAG 58%
The model gave 58% on LAG — the map was taken by LAG.
Anubisprediction correct2:13
Iowa Stormboar 29%LAG 71%
The model gave 71% on LAG — the map was taken by LAG.
Model check result
Model favoriteLAG · 71%
Series resultLAG 1:2
Series predictioncorrect
Accuracy by map3 of 3