Snow Sweet Snow #2 · BO3
result vs predictionseries probability
71%29%
probability at match start · final 2:0
The prediction was locked in using data as of the match start: hero winrates, form and head-to-head were computed only from games before it began. This is how the model's honest accuracy is verified.
Teams' go-to heroes · 6 months
Who plays what and how often they win. "Signature" — from 6 games with a 60%+ winrate: such a pick statistically raises the win chance.
No Bounty Hunter
Rubick
ntakii · 11 games
Earth Spiritsignature
dEsire · 10 games
Puckoften banned
ntakii · 10 games
Death Prophetsignature
BliNcc · 7 games
Batridersignature
ntakii · 6 games
Bloodseekersignature
BliNcc · 6 games
Grimstrokesignature
Flash · 6 games
Keeper of the Lightoften banned
Flash · 6 games
Hippomaniacs
No games played over 6 months.
Patch meta · 3 months
The most picked heroes of the pro scene and their winrate. Picking a meta hero adds points to the team in the model.
Puck
290 picks · 590 bans
Void Spirit
264 picks · 335 bans
Mars
233 picks · 415 bans
Earth Spirit
218 picks · 173 bans
Keeper of the Light
190 picks · 353 bans
Nyx Assassin
186 picks · 584 bans
Rubick
185 picks · 101 bans
Wraith King
183 picks · 245 bans
Prediction components
Form (series winrate)52% vs 28%
Hero pool strength53% No Bounty Hunter
Head-to-head1 – 0
Model total71% No Bounty Hunter
Prediction by game vs result
Probabilities were locked in using statistics as of the match start: the draft was assessed by hero comfort, counter-picks and late-game potential. We compare against the actual result.
Game 1prediction correct37:19
No Bounty Hunter 71%Hippomaniacs 29%
The model gave 71% on No Bounty Hunter — the game was taken by No Bounty Hunter in 26:10.
Game 2prediction correct45:48
No Bounty Hunter 71%Hippomaniacs 29%
The model gave 71% on No Bounty Hunter — the game was taken by No Bounty Hunter in 44:24.
Model check result
Model favoriteNo Bounty Hunter · 71%
Series resultNo Bounty Hunter 2:0
Series predictioncorrect
Accuracy by game2 of 2