European Pro League Season 5 · BO3
result vs prediction
X3win 2:0series probability
43%57%
probability at match start · final 2:0
YNTloss 0:2The 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.
X3
Tinysignature
velheor · 23 games
Marcioften banned
velheor · 21 game
Enigmaoften banned
Shergarat · 20 games
Pangoliersignature
NattyNarwhal · 20 games
Beastmasteroften banned
Shergarat · 17 games
Dawnbreakersignature
Shergarat · 16 games
Jakirosignature
dark · 15 games
Morphlingsignature
nesfeer · 13 games
YNT
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.
Tiny
366 picks · 344 bans
Tusk
323 picks · 299 bans
Marci
272 picks · 516 bans
Undying
253 picks · 465 bans
Pangolier
250 picks · 565 bans
Primal Beast
236 picks · 597 bans
Shadow Fiend
222 picks · 343 bans
Snapfire
219 picks · 119 bans
Prediction components
Form (series winrate)54% vs 57%
Hero pool strength56% X3
Head-to-head1 – 2
Model total57% YNT
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
X3 43%YNT 57%
The model gave 57% on YNT — the game was taken by X3.
Game 2prediction missed
X3 43%YNT 57%
The model gave 57% on YNT — the game was taken by X3.
Model check result
Model favoriteYNT · 57%
Series resultX3 2:0
Series predictionmissed
Accuracy by game0 of 2