?
arrow_backBack to match
European Pro League Season 28 · BO3
result vs prediction
Team Lynxloss 1:2
series probability
9%91%
probability at match start · final 1:2
MOUZwin 2:1
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.

Team Lynx

Tidehunter
Tidehunteroften banned
StoneBank · 6 games
17%
Slardar
Slardaroften banned
StoneBank · 5 games
60%
Bristleback
Bristlebackoften banned
StoneBank · 4 games
0%
Terrorblade
Terrorbladeoften banned
DarkLord^ · 4 games
25%
Medusa
Medusaoften banned
DarkLord^ · 3 games
33%
Morphling
Morphlingoften banned
DarkLord^ · 3 games
0%
Wraith King
Wraith King
StoneBank · 3 games
33%
Abaddon
Abaddonoften banned
StoneBank · 2 games
0%

MOUZ

Jakiro
Jakiro
Ekki · 13 games
46%
Magnus
Magnusoften banned
xsvampire · 12 games
58%
Phantom Assassin
Phantom Assassinoften banned
Lowskill · 11 games
36%
Ember Spirit
Ember Spiritoften banned
Supream^ · 10 games
20%
Storm Spirit
Storm Spiritoften banned
Supream^ · 10 games
20%
Abaddon
Abaddonoften banned
Kami · 9 games
44%
Beastmaster
Beastmasteroften banned
zeal · 9 games
56%
Phoenix
Phoenix
Fly · 9 games
44%
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.
Shadow Shaman
Shadow Shaman
498 picks · 536 bans
55%
Tiny
Tiny
422 picks · 432 bans
48%
Tusk
Tusk
354 picks · 357 bans
48%
Pangolier
Pangolier
343 picks · 507 bans
50%
Terrorblade
Terrorblade
326 picks · 706 bans
47%
Ringmaster
Ringmaster
311 picks · 178 bans
51%
Storm Spirit
Storm Spirit
299 picks · 438 bans
48%
Nature's Prophet
Nature's Prophet
298 picks · 553 bans
52%
Prediction components
Form (series winrate)33% vs 39%
Hero pool strength52% MOUZ
Head-to-head0 – 0
Model total91% MOUZ
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 correct
Team Lynx 9%MOUZ 91%
The model gave 91% on MOUZ — the game was taken by MOUZ.
Game 2prediction missed
Team Lynx 9%MOUZ 91%
The model gave 91% on MOUZ — the game was taken by Team Lynx.
Game 3prediction correct
Team Lynx 9%MOUZ 91%
The model gave 91% on MOUZ — the game was taken by MOUZ.
Model check result
Model favoriteMOUZ · 91%
Series resultMOUZ 1:2
Series predictioncorrect
Accuracy by game2 of 3