?
The International 10 (2021) · BO3
result vs prediction
T1win 2:0
series probability
69%31%
probability at match start · final 2:0
Allianceloss 0:2
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.

T1

No games played over 6 months.

Alliance

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.
Lion
Lion
303 picks · 179 bans
53%
Mars
Mars
292 picks · 405 bans
49%
Lina
Lina
277 picks · 568 bans
56%
Pangolier
Pangolier
259 picks · 367 bans
51%
Shadow Demon
Shadow Demon
249 picks · 254 bans
58%
Tidehunter
Tidehunter
245 picks · 412 bans
51%
Hoodwink
Hoodwink
242 picks · 88 bans
45%
Void Spirit
Void Spirit
229 picks · 256 bans
53%
Prediction components
Form (series winrate)49% vs 26%
Hero pool strength50% T1
Head-to-head3 – 0
Model total69% 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 missed13:35
T1 69%Alliance 31%
The model gave 69% on T1 — the game was taken by Alliance in 37:05.
Game 2prediction missed15:44
T1 69%Alliance 31%
The model gave 69% on T1 — the game was taken by Alliance in 33:58.
Model check result
Model favoriteT1 · 69%
Series resultT1 2:0
Series predictioncorrect
Accuracy by game0 of 2