European Pro League Season 5 · BO3
result vs prediction
CYBER UNIONloss 0:2series probability
52%48%
probability at match start · final 0:2
Level UPwin 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.
CYBER UNION
Tiny
Miyaoo · 14 games
Silenceroften banned
Arti_Shock · 12 games
Tusk
OneJey · 10 games
Lich
Arti_Shock · 6 games
Primal Beastoften banned
klassnokruto · 6 games
Clockwerk
OneJey · 5 games
Death Prophetoften banned
Miyaoo · 5 games
Pudgeoften banned
dizzying · 5 games
Level UP
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.
Tiny
370 picks · 346 bans
Tusk
328 picks · 303 bans
Marci
272 picks · 510 bans
Pangolier
250 picks · 569 bans
Undying
250 picks · 463 bans
Primal Beast
237 picks · 600 bans
Snapfire
220 picks · 122 bans
Shadow Fiend
219 picks · 344 bans
Prediction components
Form (series winrate)45% vs 33%
Hero pool strength57% Level UP
Head-to-head0 – 0
Model total52% CYBER UNION
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 missed
CYBER UNION 52%Level UP 48%
The model gave 52% on CYBER UNION — the game was taken by Level UP.
Game 2prediction missed
CYBER UNION 52%Level UP 48%
The model gave 52% on CYBER UNION — the game was taken by Level UP.
Model check result
Model favoriteCYBER UNION · 52%
Series resultLevel UP 0:2
Series predictionmissed
Accuracy by game0 of 2