?
arrow_backBack to match
NODWIN Clutch Series 9 Closed Qualifier · BO3
result vs prediction
MANA#86 in the world · win 2:1
series probability
30%70%
probability at match start · final 2:1
Falcons Force#152 in the world · loss 1:2
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
40%38%
MANA · 6 mapsnearly even +2%Falcons Force · 4 maps
MirageMANA pick
45%57%
MANA · 7 mapsedge Falcons Force +12%Falcons Force · 3 maps
AncientFalcons Force pick
25%33%
MANA · 4 mapsedge Falcons Force +8%Falcons Force · 5 maps
AnubisMANA ban
50%40%
MANA · 4 mapsedge MANA +10%Falcons Force · 1 map
NukeFalcons Force ban
50%33%
MANA · 2 mapsedge MANA +17%Falcons Force · 2 maps
InfernoFalcons Force ban
50%50%
MANA · 2 mapsnearly even +0%Falcons Force · 0 maps
OverpassMANA ban
40%50%
MANA · 1 mapedge Falcons Force +10%Falcons Force · 0 maps
Most likely veto scenario
1. BanMANA remove Overpass
2. BanFalcons Force remove Inferno
3. PickMANA take Mirage
4. PickFalcons Force take Ancient
5. BanFalcons Force remove Nuke
6. BanMANA remove Anubis
DeciderDust2 (40% / 38%)
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.
Ancientprediction correct10:13
MANA 37%Falcons Force 63%
The model gave 63% on Falcons Force — the map was taken by Falcons Force.
Dust2prediction correct13:7
MANA 56%Falcons Force 44%
The model gave 56% on MANA — the map was taken by MANA.
Mirageprediction missed13:6
MANA 38%Falcons Force 62%
The model gave 62% on Falcons Force — the map was taken by MANA.
Model check result
Model favoriteFalcons Force · 70%
Series resultMANA 2:1
Series predictionmissed
Accuracy by map2 of 3