ESEA Season 58 Europe Finals · BO3
result vs prediction
Fire Flux#103 in the world · win 2:1series probability
66%34%
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.
Dust2possible decider
50%43%
Fire Flux · 14 mapsedge Fire Flux +7%NAVI Junior · 17 maps
MirageNAVI Junior pick
47%73%
Fire Flux · 11 mapsedge NAVI Junior +26%NAVI Junior · 18 maps
AnubisFire Flux pick
69%53%
Fire Flux · 12 mapsedge Fire Flux +16%NAVI Junior · 11 maps
NukeFire Flux ban
55%38%
Fire Flux · 7 mapsedge Fire Flux +17%NAVI Junior · 9 maps
AncientFire Flux ban
25%29%
Fire Flux · 4 mapsnearly even -4%NAVI Junior · 10 maps
CacheNAVI Junior ban
57%43%
Fire Flux · 10 mapsedge Fire Flux +14%NAVI Junior · 3 maps
InfernoNAVI Junior ban
64%33%
Fire Flux · 10 mapsedge Fire Flux +31%NAVI Junior · 2 maps
Most likely veto scenario
1. BanFire Flux remove Ancient
2. BanNAVI Junior remove Cache
3. PickFire Flux take Anubis
4. PickNAVI Junior take Mirage
5. BanNAVI Junior remove Inferno
6. BanFire Flux remove Nuke
DeciderDust2 (50% / 43%)
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 missed13:5
Fire Flux 23%NAVI Junior 77%
The model gave 77% on NAVI Junior — the map was taken by Fire Flux.
Anubisprediction missed9:13
Fire Flux 68%NAVI Junior 32%
The model gave 68% on Fire Flux — the map was taken by NAVI Junior.
Dust2prediction correct13:8
Fire Flux 57%NAVI Junior 43%
The model gave 57% on Fire Flux — the map was taken by Fire Flux.
Model check result
Model favoriteFire Flux · 66%
Series resultFire Flux 2:1
Series predictioncorrect
Accuracy by map1 of 3