?
FISSURE Universe: Episode 3 · BO3
result vs prediction
Yellow Submarineloss 0:1
series probability
42%58%
probability at match start · final 0:1
nounswin 1:0
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.

Yellow Submarine

Crystal Maiden
Crystal Maiden
asdekor_r · 33 games
45%
Centaur Warrunner
Centaur Warrunnersignature
emptiness · 29 games
62%
Pangolier
Pangoliersignature
erase · 27 games
67%
Enchantress
Enchantressoften banned
asdekor_r · 26 games
58%
Techies
Techies
rue · 25 games
52%
Rubick
Rubick
rue · 20 games
45%
Shadow Demon
Shadow Demonoften banned
rue · 20 games
55%
Hoodwink
Hoodwinksignature
rue · 19 games
63%

nouns

Crystal Maiden
Crystal Maiden
Fly · 27 games
59%
Tiny
Tinysignature
Copy · 27 games
67%
Rubick
Rubick
Lelis · 25 games
56%
Dragon Knight
Dragon Knightoften banned
Yuma · 20 games
45%
Pangolier
Pangoliersignature
Copy · 20 games
60%
Phoenix
Phoenixoften banned
Fly · 19 games
53%
Sven
Svenoften banned
Yuma · 19 games
58%
Centaur Warrunner
Centaur Warrunnersignature
Gunnar · 18 games
72%
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.
Rubick
Rubick
435 picks · 366 bans
51%
Hoodwink
Hoodwink
423 picks · 461 bans
53%
Weaver
Weaver
389 picks · 838 bans
55%
Tiny
Tiny
387 picks · 872 bans
54%
Phoenix
Phoenix
370 picks · 768 bans
50%
Pangolier
Pangolier
361 picks · 535 bans
48%
Clockwerk
Clockwerk
340 picks · 509 bans
56%
Ember Spirit
Ember Spirit
325 picks · 623 bans
50%
Prediction components
Form (series winrate)51% vs 47%
Hero pool strength52% nouns
Head-to-head0 – 0
Model total58% nouns
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 correct
Yellow Submarine 42%nouns 58%
The model gave 58% on nouns — the game was taken by nouns.
Model check result
Model favoritenouns · 58%
Series resultnouns 0:1
Series predictioncorrect
Accuracy by game1 of 1