European Pro League Season 18 · BO3
result vs prediction
1w Teamwin 2:0series probability
59%41%
probability at match start · final 2:0
Rest Farmersloss 0:2The 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.
1w Team
Gyrocoptersignature
RESPECT · 27 games
Pangolieroften banned
Chira JUNIOR · 26 games
Tinysignature
Chira JUNIOR · 25 games
Lunasignature
Munkushi~ · 21 game
Crystal Maiden
RESPECT · 20 games
Marsoften banned
Cloud · 19 games
Templar Assassinoften banned
Chira JUNIOR · 19 games
Magnussignature
Cloud · 18 games
Rest Farmers
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.
Crystal Maiden
467 picks · 200 bans
Tiny
430 picks · 581 bans
Batrider
420 picks · 768 bans
Centaur Warrunner
409 picks · 585 bans
Rubick
399 picks · 164 bans
Pangolier
363 picks · 707 bans
Mars
354 picks · 577 bans
Dragon Knight
343 picks · 1077 bans
Prediction components
Form (series winrate)37% vs 53%
Hero pool strength55% 1w Team
Head-to-head0 – 0
Model total59% 1w Team
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 correct28:13
1w Team 59%Rest Farmers 41%
The model gave 59% on 1w Team — the game was taken by 1w Team in 40:15.
Game 2prediction correct39:24
1w Team 59%Rest Farmers 41%
The model gave 59% on 1w Team — the game was taken by 1w Team in 41:29.
Model check result
Model favorite1w Team · 59%
Series result1w Team 2:0
Series predictioncorrect
Accuracy by game2 of 2