Tipsport Open Cup 1 · BO3
result vs predictionseries probability
43%57%
probability at match start · final 2:0
UNiTY#102 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.
AncientJam pick
75%69%
Jam · 4 mapsedge Jam +6%UNiTY · 9 maps
MirageJam ban
50%36%
Jam · 2 mapsedge Jam +14%UNiTY · 7 maps
AnubisUNiTY ban
71%44%
Jam · 3 mapsedge Jam +27%UNiTY · 5 maps
Dust2possible decider
60%50%
Jam · 1 mapedge Jam +10%UNiTY · 6 maps
CacheJam ban
50%38%
Jam · 0 mapsedge Jam +12%UNiTY · 4 maps
InfernoUNiTY pick
50%50%
Jam · 0 mapsnearly even +0%UNiTY · 4 maps
NukeUNiTY ban
71%40%
Jam · 3 mapsedge Jam +31%UNiTY · 1 map
Most likely veto scenario
1. BanJam remove Cache
2. BanUNiTY remove Nuke
3. PickJam take Ancient
4. PickUNiTY take Inferno
5. BanUNiTY remove Anubis
6. BanJam remove Mirage
DeciderDust2 (60% / 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.
Dust2prediction correct13:10
Jam 63%UNiTY 37%
The model gave 63% on Jam — the map was taken by Jam.
Infernoprediction missed13:2
Jam 47%UNiTY 53%
The model gave 53% on UNiTY — the map was taken by Jam.
Model check result
Model favoriteUNiTY · 57%
Series resultJam 2:0
Series predictionmissed
Accuracy by map1 of 2