The International 2022: Last Chance · BO2
result vs prediction
Tempestloss 1:1series probability
43%57%
probability at match start · final 1:1
nounsloss 1:1The 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.
Tempest
No games played over 6 months.
nouns
Dragon Knightsignature
Moo · 12 games
Enigmasignature
ZfreeK · 11 games
Tinysignature
ZfreeK · 11 games
Enchantressoften banned
Husky · 9 games
Marcioften banned
ZfreeK · 9 games
Pangoliersignature
Gunnar · 9 games
Tusksignature
Gunnar · 9 games
Winter Wyvernoften banned
Husky · 9 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.
Tiny
548 picks · 424 bans
Marci
458 picks · 660 bans
Puck
332 picks · 754 bans
Dawnbreaker
330 picks · 452 bans
Death Prophet
299 picks · 493 bans
Winter Wyvern
290 picks · 363 bans
Batrider
258 picks · 832 bans
Dazzle
250 picks · 160 bans
Prediction components
Form (series winrate)44% vs 56%
Hero pool strength57% nouns
Head-to-head0 – 0
Model total57% nouns
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 correct50:10
Tempest 43%nouns 57%
The model gave 57% on nouns — the game was taken by nouns in 43:01.
Game 2prediction correct29:40
Tempest 43%nouns 57%
The model gave 57% on nouns — the game was taken by nouns in 41:09.
Model check result
Model favoritenouns · 57%
Accuracy by game2 of 2