European Pro League Season 22 · BO3
result vs prediction
TT Teamloss 0:2series probability
12%88%
probability at match start · final 0:2
MOUZwin 2:0The 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.
TT Team
Batrideroften banned
Askold · 1 game
MOUZ
Gyrocopteroften banned
Ulnit · 24 games
Pangolieroften banned
Force · 24 games
Witch Doctor
bengan · 24 games
Dragon Knightoften banned
Supream^ · 23 games
Dark Willow
NARMAN · 21 game
Jakiro
bengan · 21 game
Primal Beastoften banned
Force · 20 games
Tuskoften banned
bengan · 20 games
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
481 picks · 663 bans
Clockwerk
431 picks · 504 bans
Pangolier
377 picks · 549 bans
Dark Willow
363 picks · 185 bans
Batrider
333 picks · 359 bans
Luna
326 picks · 432 bans
Invoker
314 picks · 865 bans
Dragon Knight
309 picks · 604 bans
Prediction components
Form (series winrate)38% vs 49%
Hero pool strength53% MOUZ
Head-to-head0 – 0
Model total88% 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 correct19:46
TT Team 12%MOUZ 88%
The model gave 88% on MOUZ — the game was taken by MOUZ in 33:09.
Game 2prediction correct28:43
TT Team 12%MOUZ 88%
The model gave 88% on MOUZ — the game was taken by MOUZ in 44:43.
Model check result
Model favoriteMOUZ · 88%
Series resultMOUZ 0:2
Series predictioncorrect
Accuracy by game2 of 2