?
The International 10 (2021) · BO1
result vs prediction
beastcoastloss 0:1
series probability
50%50%
probability at match start · final 0:1
Alliancewin 1:0
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.

beastcoast

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
301 picks · 179 bans
53%
Mars
Mars
290 picks · 402 bans
49%
Lina
Lina
276 picks · 565 bans
56%
Pangolier
Pangolier
260 picks · 368 bans
51%
Shadow Demon
Shadow Demon
247 picks · 253 bans
58%
Hoodwink
Hoodwink
243 picks · 89 bans
45%
Tidehunter
Tidehunter
241 picks · 409 bans
52%
Void Spirit
Void Spirit
225 picks · 256 bans
52%
Prediction components
Form (series winrate)25% vs 22%
Hero pool strength50% beastcoast
Head-to-head0 – 0
Model total50% 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 correct45:19
beastcoast 50%Alliance 50%
The model gave 50% on Alliance — the game was taken by Alliance in 43:57.
Model check result
Model favoriteAlliance · 50%
Series resultAlliance 0:1
Series predictioncorrect
Accuracy by game1 of 1