EPL Masters I. Play-In · BO3
result vs predictionTJTeam Jenzwin 2:1
series probability
86%14%
probability at match start · final 2:1
KKWloss 1:2
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.
Team Jenz
Lina
No!ob · 5 games
Luna
Parker · 4 games
Shadow Demon
Jing · 3 games
Snapfireoften banned
No!ob · 3 games
Clockwerkoften banned
Yadomi · 2 games
Omniknight
Yadomi · 2 games
Ringmaster
Jing · 2 games
Beastmasteroften banned
No!ob · 1 game
KW
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.
Hoodwink
497 picks · 358 bans
Rubick
401 picks · 241 bans
Tiny
343 picks · 354 bans
Clockwerk
334 picks · 631 bans
Windranger
322 picks · 233 bans
Pangolier
306 picks · 407 bans
Bane
286 picks · 273 bans
Storm Spirit
286 picks · 307 bans
Prediction components
Form (series winrate)57% vs 50%
Hero pool strength57% Team Jenz
Head-to-head0 – 0
Model total86% Team Jenz
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 missed
Team Jenz 86%KW 14%
The model gave 86% on Team Jenz — the game was taken by KW.
Game 2prediction correct
Team Jenz 86%KW 14%
The model gave 86% on Team Jenz — the game was taken by Team Jenz.
Game 3prediction correct
Team Jenz 86%KW 14%
The model gave 86% on Team Jenz — the game was taken by Team Jenz.
Model check result
Model favoriteTeam Jenz · 86%
Series resultTeam Jenz 2:1
Series predictioncorrect
Accuracy by game2 of 3