DreamLeague Season 19 · BO2
result vs prediction
beastcoastloss 1:1series probability
48%52%
probability at match start · final 1:1
nounsloss 1:1The 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.
beastcoast
No games played over 6 months.
nouns
Undyingoften banned
Husky · 17 games
Rubicksignature
Lelis · 16 games
Tusk
Gunnar · 12 games
Tiny
Lelis · 11 games
Snapfire
Lelis · 8 games
Doomsignature
Moo · 7 games
Leshracsignature
Gunnar · 7 games
Nature's Prophetoften banned
Moo · 7 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.
Rubick
974 picks · 663 bans
Tiny
659 picks · 474 bans
Nature's Prophet
584 picks · 937 bans
Tusk
555 picks · 439 bans
Treant Protector
527 picks · 523 bans
Snapfire
522 picks · 347 bans
Death Prophet
505 picks · 1113 bans
Clockwerk
477 picks · 350 bans
Prediction components
Form (series winrate)57% vs 54%
Hero pool strength54% nouns
Head-to-head0 – 1
Model total52% nouns
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 correct39:21
beastcoast 48%nouns 52%
The model gave 52% on nouns — the game was taken by nouns in 51:11.
Game 2prediction correct24:18
beastcoast 48%nouns 52%
The model gave 52% on nouns — the game was taken by nouns in 34:42.
Model check result
Model favoritenouns · 52%
Accuracy by game2 of 2