?
Dota Pro Circuit 2021/2022 — Северная Америка. Финал · BO3
result vs prediction
TSMwin 2:0
series probability
32%68%
probability at match start · final 2:0
Evil Geniusesloss 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.

TSM

Bane
Bane
DuBu · 10 games
50%
Weaver
Weaversignature
MoonMeander · 9 games
67%
Mirana
Miranasignature
MoonMeander · 8 games
63%
Pangolier
Pangolieroften banned
SabeRLight- · 8 games
38%
Tidehunter
Tidehuntersignature
SabeRLight- · 7 games
86%
Disruptor
Disruptorsignature
DuBu · 6 games
67%
Grimstroke
Grimstrokesignature
MoonMeander · 6 games
67%
Io
Iosignature
MoonMeander · 6 games
83%

Evil Geniuses

Mars
Marsoften banned
Tavo · 10 games
10%
Io
Iooften banned
KJ · 9 games
11%
Mirana
Mirana
Thiolicor · 8 games
38%
Sven
Svensignature
Costabile · 8 games
63%
Gyrocopter
Gyrocopter
Costabile · 7 games
0%
Doom
Doomoften banned
Hyko · 6 games
17%
Invoker
Invokeroften banned
4dr · 6 games
50%
Ogre Magi
Ogre Magi
KJ · 6 games
0%
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.
Bane
Bane
541 picks · 390 bans
57%
Mars
Mars
452 picks · 651 bans
52%
Queen of Pain
Queen of Pain
452 picks · 553 bans
52%
Weaver
Weaver
434 picks · 851 bans
55%
Snapfire
Snapfire
353 picks · 183 bans
45%
Spirit Breaker
Spirit Breaker
345 picks · 560 bans
53%
Kunkka
Kunkka
340 picks · 542 bans
54%
Wraith King
Wraith King
279 picks · 318 bans
55%
Prediction components
Form (series winrate)50% vs 58%
Hero pool strength67% TSM
Head-to-head0 – 0
Model total68% Evil Geniuses
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 missed32:14
TSM 32%Evil Geniuses 68%
The model gave 68% on Evil Geniuses — the game was taken by TSM in 37:15.
Game 2prediction missed29:12
TSM 32%Evil Geniuses 68%
The model gave 68% on Evil Geniuses — the game was taken by TSM in 28:16.
Model check result
Model favoriteEvil Geniuses · 68%
Series resultTSM 2:0
Series predictionmissed
Accuracy by game0 of 2