The International 10 (2021) · BO2
result vs predictionseries probability
57%43%
probability at match start · final 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.
Alliance
No games played over 6 months.
Thunder Awaken
Marsoften banned
Frank · 11 games
Phoenixoften banned
Mjz · 8 games
Earth Spirit
MoOz · 5 games
Void Spiritoften banned
Leostyle · 5 games
Batrideroften banned
Leostyle · 4 games
Centaur Warrunner
Frank · 4 games
Dark Willow
MoOz · 4 games
Linaoften banned
MoOz · 4 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.
Lion
310 picks · 179 bans
Mars
286 picks · 407 bans
Lina
283 picks · 541 bans
Hoodwink
269 picks · 92 bans
Pangolier
263 picks · 371 bans
Shadow Demon
245 picks · 258 bans
Luna
230 picks · 328 bans
Tidehunter
216 picks · 375 bans
Prediction components
Form (series winrate)25% vs 17%
Hero pool strength55% Alliance
Head-to-head0 – 1
Model total57% Alliance
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 correct42:34
Alliance 57%Thunder Awaken 43%
The model gave 57% on Alliance — the game was taken by Alliance in 56:00.
Game 2prediction correct34:19
Alliance 57%Thunder Awaken 43%
The model gave 57% on Alliance — the game was taken by Alliance in 27:19.
Model check result
Model favoriteAlliance · 57%
Series resultAlliance 2:0
Series predictioncorrect
Accuracy by game2 of 2