The International 2022. Региональные отборочные · BO3
result vs prediction
No Runesloss 1:2series probability
37%63%
probability at match start · final 1:2
SG e-sportswin 2:1The 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.
No Runes
No games played over 6 months.
SG e-sports
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
724 picks · 570 bans
Puck
511 picks · 1027 bans
Dawnbreaker
480 picks · 631 bans
Marci
441 picks · 786 bans
Winter Wyvern
373 picks · 413 bans
Snapfire
335 picks · 163 bans
Zeus
327 picks · 381 bans
Razor
310 picks · 590 bans
Prediction components
Form (series winrate)50% vs 33%
Hero pool strength50% No Runes
Head-to-head0 – 0
Model total63% SG e-sports
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 correct10:31
No Runes 37%SG e-sports 63%
The model gave 63% on SG e-sports — the game was taken by SG e-sports in 35:59.
Game 2prediction correct20:6
No Runes 37%SG e-sports 63%
The model gave 63% on SG e-sports — the game was taken by SG e-sports in 33:35.
Game 3prediction correct36:29
No Runes 37%SG e-sports 63%
The model gave 63% on SG e-sports — the game was taken by SG e-sports in 46:16.
Model check result
Model favoriteSG e-sports · 63%
Series resultSG e-sports 1:2
Series predictioncorrect
Accuracy by game3 of 3