?
The International 2022. Региональные отборочные · BO3
result vs prediction
RSGloss 0:2
series probability
34%66%
probability at match start · final 0:2
T1win 2:0
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.

RSG

No games played over 6 months.

T1

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
Tiny
710 picks · 558 bans
53%
Dawnbreaker
Dawnbreaker
500 picks · 656 bans
45%
Marci
Marci
496 picks · 780 bans
52%
Puck
Puck
476 picks · 1003 bans
55%
Winter Wyvern
Winter Wyvern
371 picks · 420 bans
54%
Zeus
Zeus
326 picks · 398 bans
46%
Snapfire
Snapfire
312 picks · 156 bans
49%
Razor
Razor
297 picks · 560 bans
52%
Prediction components
Form (series winrate)47% vs 53%
Hero pool strength50% RSG
Head-to-head1 – 1
Model total66% T1
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 correct41:18
RSG 34%T1 66%
The model gave 66% on T1 — the game was taken by T1 in 45:30.
Game 2prediction correct24:13
RSG 34%T1 66%
The model gave 66% on T1 — the game was taken by T1 in 34:03.
Model check result
Model favoriteT1 · 66%
Series resultT1 0:2
Series predictioncorrect
Accuracy by game2 of 2