Elite League · BO2
result vs predictionseries probability
47%53%
probability at match start · final 1:1
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.
Aurora Gaming
No games played over 6 months.
Team Liquid
Lunasignature
miCKe · 23 games
Vengeful Spiritsignature
iNSaNiA · 21 game
Rubick
Boxi · 19 games
Pangoliersignature
Nisha · 15 games
Brewmastersignature
33 · 14 games
Muerta
Boxi · 13 games
Templar Assassinsignature
miCKe · 13 games
Doomoften banned
33 · 12 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.
Centaur Warrunner
497 picks · 784 bans
Batrider
459 picks · 965 bans
Techies
455 picks · 351 bans
Crystal Maiden
453 picks · 196 bans
Mars
450 picks · 717 bans
Tiny
449 picks · 598 bans
Rubick
437 picks · 205 bans
Pangolier
424 picks · 714 bans
Prediction components
Form (series winrate)40% vs 48%
Hero pool strength56% Team Liquid
Head-to-head1 – 0
Model total53% Team Liquid
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 correct16:24
Aurora Gaming 47%Team Liquid 53%
The model gave 53% on Team Liquid — the game was taken by Team Liquid in 37:19.
Game 2prediction correct26:9
Aurora Gaming 47%Team Liquid 53%
The model gave 53% on Team Liquid — the game was taken by Team Liquid in 41:30.
Model check result
Model favoriteTeam Liquid · 53%
Accuracy by game2 of 2