European Pro League Season 23 · BO3
result vs predictionseries probability
74%26%
probability at match start · final 2:0
Xxanblloss 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.
ASAKURA
Brewmasteroften banned
Infernal · 5 games
Invokeroften banned
young G · 5 games
Lion
slimeyao · 5 games
Magnusoften banned
Infernal · 4 games
Morphlingoften banned
7jesu · 4 games
Tidehunteroften banned
Palantimos · 4 games
Bounty Hunter
333 · 3 games
Clockwerkoften banned
so bad · 3 games
xanbl
No games played over 6 months.
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.
Muerta
485 picks · 409 bans
Clockwerk
451 picks · 582 bans
Batrider
422 picks · 524 bans
Lion
414 picks · 227 bans
Gyrocopter
412 picks · 694 bans
Phoenix
404 picks · 461 bans
Pangolier
374 picks · 595 bans
Beastmaster
357 picks · 932 bans
Prediction components
Form (series winrate)58% vs 45%
Hero pool strength53% ASAKURA
Head-to-head0 – 1
Model total74% ASAKURA
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 correct37:15
ASAKURA 74%xanbl 26%
The model gave 74% on ASAKURA — the game was taken by ASAKURA in 35:22.
Game 2prediction correct50:44
ASAKURA 74%xanbl 26%
The model gave 74% on ASAKURA — the game was taken by ASAKURA in 1:00:04.
Model check result
Model favoriteASAKURA · 74%
Series resultASAKURA 2:0
Series predictioncorrect
Accuracy by game2 of 2