The International 2022: Last Chance · BO2
result vs prediction
T1loss 1:1series probability
42%58%
probability at match start · final 1:1
Virtus.proloss 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.
T1
No games played over 6 months.
Virtus.pro
Marcisignature
yamich · 23 games
Skywrath Magesignature
Xakoda · 17 games
Doomsignature
DM · 16 games
Dragon Knightsignature
DM · 16 games
Templar Assassinsignature
gpK~ · 15 games
Tinysignature
yamich · 15 games
Dazzlesignature
Xakoda · 14 games
Snapfire
Xakoda · 14 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
457 picks · 665 bans
Puck
332 picks · 753 bans
Dawnbreaker
329 picks · 452 bans
Death Prophet
299 picks · 493 bans
Winter Wyvern
291 picks · 361 bans
Batrider
258 picks · 834 bans
Dazzle
251 picks · 160 bans
Prediction components
Form (series winrate)44% vs 55%
Hero pool strength61% Virtus.pro
Head-to-head0 – 0
Model total58% Virtus.pro
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 correct35:37
T1 42%Virtus.pro 58%
The model gave 58% on Virtus.pro — the game was taken by Virtus.pro in 50:26.
Game 2prediction correct47:28
T1 42%Virtus.pro 58%
The model gave 58% on Virtus.pro — the game was taken by Virtus.pro in 48:26.
Model check result
Model favoriteVirtus.pro · 58%
Accuracy by game2 of 2