?
arrow_backBack to match
European Pro League Season 22 · BO3
result vs prediction
Hydrawin 2:1
series probability
35%65%
probability at match start · final 2:1
MOUZloss 1:2
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.

Hydra

Dark Willow
Dark Willow
ani-san · 7 games
57%
Morphling
Morphlingoften banned
selfhate · 7 games
43%
Queen of Pain
Queen of Painoften banned
Ethereal · 7 games
29%
Underlord
Underlord
Actor · 7 games
29%
Invoker
Invokeroften banned
Ethereal · 5 games
60%
Primal Beast
Primal Beastoften banned
Actor · 5 games
20%
Snapfire
Snapfire
ani-san · 5 games
20%
Centaur Warrunner
Centaur Warrunneroften banned
Actor · 4 games
25%

MOUZ

Gyrocopter
Gyrocopteroften banned
Ulnit · 25 games
40%
Pangolier
Pangolieroften banned
Force · 24 games
29%
Witch Doctor
Witch Doctor
bengan · 24 games
50%
Dragon Knight
Dragon Knightoften banned
Supream^ · 23 games
48%
Dark Willow
Dark Willow
NARMAN · 21 game
43%
Jakiro
Jakiro
bengan · 21 game
43%
Primal Beast
Primal Beastoften banned
Force · 20 games
45%
Tusk
Tuskoften banned
bengan · 20 games
35%
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.
Tusk
Tusk
486 picks · 670 bans
51%
Clockwerk
Clockwerk
423 picks · 496 bans
55%
Pangolier
Pangolier
374 picks · 539 bans
48%
Dark Willow
Dark Willow
358 picks · 184 bans
50%
Luna
Luna
331 picks · 438 bans
54%
Batrider
Batrider
328 picks · 350 bans
49%
Enchantress
Enchantress
316 picks · 597 bans
53%
Dragon Knight
Dragon Knight
310 picks · 557 bans
54%
Prediction components
Form (series winrate)52% vs 49%
Hero pool strength52% MOUZ
Head-to-head0 – 0
Model total65% MOUZ
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
Hydra 35%MOUZ 65%
The model gave 65% on MOUZ — the game was taken by MOUZ.
Game 2prediction missed
Hydra 35%MOUZ 65%
The model gave 65% on MOUZ — the game was taken by Hydra.
Game 3prediction missed
Hydra 35%MOUZ 65%
The model gave 65% on MOUZ — the game was taken by Hydra.
Model check result
Model favoriteMOUZ · 65%
Series resultHydra 2:1
Series predictionmissed
Accuracy by game1 of 3