European Pro League Season 35 · BO3
result vs predictionseries probability
26%74%
probability at match start · final 0:2
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.
DOGSENT
Shadow Shaman
islA · 1 game
Void Spirit
islA · 1 game
Level UP
Dragon Knightoften banned
MaTson · 6 games
Tusk
Gilgir · 6 games
Batrideroften banned
Atoufix · 5 games
Centaur Warrunneroften banned
pJonn · 5 games
Pangolieroften banned
MaTson · 5 games
Puckoften banned
MaTson · 5 games
Pugna
kur0patbI4 · 5 games
Shadow Fiendoften banned
Rain · 5 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.
Jakiro
599 picks · 938 bans
Tusk
487 picks · 434 bans
Tiny
466 picks · 506 bans
Warlock
434 picks · 285 bans
Shadow Demon
427 picks · 1050 bans
Centaur Warrunner
414 picks · 589 bans
Ember Spirit
392 picks · 676 bans
Mars
388 picks · 572 bans
Prediction components
Form (series winrate)27% vs 36%
Hero pool strength54% DOGSENT
Head-to-head0 – 1
Model total74% Level UP
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
DOGSENT 26%Level UP 74%
The model gave 74% on Level UP — the game was taken by Level UP.
Game 2prediction correct
DOGSENT 26%Level UP 74%
The model gave 74% on Level UP — the game was taken by Level UP.
Model check result
Model favoriteLevel UP · 74%
Series resultLevel UP 0:2
Series predictioncorrect
Accuracy by game2 of 2