Snow Sweet Snow #1 · BO3
result vs predictionBburjuiloss 0:1
series probability
57%43%
probability at match start · final 0:1
Bramewin 1:0The 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.
burjui
Disruptor
Atoufix · 1 game
Drow Rangeroften banned
Max · 1 game
Juggernautoften banned
Max · 1 game
Lycanoften banned
Symmetrical · 1 game
Oracle
Atoufix · 1 game
Outworld Destroyeroften banned
Symmetrical · 1 game
Puckoften banned
KiLLoManceR · 1 game
Rubick
KiLLoManceR · 1 game
Brame
Earth Spirit
CTOMAHEH1 · 4 games
Enigmaoften banned
SkyLark · 3 games
Beastmasteroften banned
SkyLark · 2 games
Enchantressoften banned
SsaSpartan · 2 games
Puckoften banned
W1sh- · 2 games
Ursaoften banned
Focus · 2 games
Bristlebackoften banned
W1sh- · 1 game
Elder Titan
SsaSpartan · 1 game
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.
Mars
77 picks · 157 bans
Puck
74 picks · 183 bans
Earth Spirit
64 picks · 54 bans
Void Spirit
57 picks · 112 bans
Rubick
52 picks · 29 bans
Undying
51 picks · 70 bans
Monkey King
48 picks · 111 bans
Phoenix
47 picks · 65 bans
Prediction components
Form (series winrate)50% vs 38%
Hero pool strength52% Brame
Head-to-head0 – 1
Model total57% burjui
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 missed
burjui 57%Brame 43%
The model gave 57% on burjui — the game was taken by Brame.
Model check result
Model favoriteburjui · 57%
Series resultBrame 0:1
Series predictionmissed
Accuracy by game0 of 1