European Pro League Season 37 · BO3
result vs predictionseries probability
78%22%
probability at match start · final 2:1
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.
Two Move
Hoodwink
queezy · 2 games
Bloodseekeroften banned
WoE · 1 game
Brewmasteroften banned
Bb3px · 1 game
Death Prophet
Ainkrad · 1 game
Ember Spiritoften banned
Ainkrad · 1 game
Faceless Voidoften banned
WoE · 1 game
Ringmaster
Htrd · 1 game
Silencer
Htrd · 1 game
Enjoy Boys
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.
Hoodwink
510 picks · 282 bans
Phoenix
481 picks · 565 bans
Tiny
439 picks · 350 bans
Jakiro
436 picks · 343 bans
Tusk
373 picks · 326 bans
Beastmaster
346 picks · 836 bans
Puck
346 picks · 841 bans
Rubick
339 picks · 178 bans
Prediction components
Form (series winrate)78% vs 46%
Hero pool strength58% Two Move
Head-to-head0 – 0
Model total78% Two Move
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 missed7:28
Two Move 78%Enjoy Boys 22%
The model gave 78% on Two Move — the game was taken by Enjoy Boys in 36:22.
Game 2prediction correct29:9
Two Move 78%Enjoy Boys 22%
The model gave 78% on Two Move — the game was taken by Two Move in 31:58.
Game 3prediction correct32:12
Two Move 78%Enjoy Boys 22%
The model gave 78% on Two Move — the game was taken by Two Move in 35:07.
Model check result
Model favoriteTwo Move · 78%
Series resultTwo Move 2:1
Series predictioncorrect
Accuracy by game2 of 3