?
arrow_backBack to match
European Pro League Season 5 · BO3
result vs prediction
IVYloss 1:2
series probability
47%53%
probability at match start · final 1:2
X3win 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.

IVY

Tiny
Tiny
Qupe · 34 games
53%
Mirana
Mirana
Qupe · 26 games
54%
Timbersaw
Timbersawsignature
Mo13ei · 20 games
65%
Clockwerk
Clockwerksignature
Qupe · 19 games
63%
Snapfire
Snapfire
Qupe · 17 games
59%
Viper
Viperoften banned
Max · 15 games
53%
Chen
Chenoften banned
jmn- · 14 games
43%
Death Prophet
Death Prophetoften banned
Mo13ei · 13 games
15%

X3

Tiny
Tinysignature
velheor · 23 games
61%
Marci
Marcioften banned
velheor · 21 game
52%
Pangolier
Pangoliersignature
NattyNarwhal · 20 games
60%
Enigma
Enigmaoften banned
Shergarat · 19 games
53%
Beastmaster
Beastmasteroften banned
Shergarat · 17 games
53%
Jakiro
Jakirosignature
dark · 15 games
60%
Dawnbreaker
Dawnbreakersignature
Shergarat · 14 games
64%
Morphling
Morphlingsignature
nesfeer · 13 games
69%
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
Tiny
372 picks · 356 bans
48%
Tusk
Tusk
337 picks · 319 bans
59%
Marci
Marci
264 picks · 501 bans
54%
Pangolier
Pangolier
250 picks · 575 bans
53%
Undying
Undying
247 picks · 459 bans
52%
Primal Beast
Primal Beast
236 picks · 602 bans
53%
Snapfire
Snapfire
222 picks · 128 bans
47%
Shadow Fiend
Shadow Fiend
217 picks · 353 bans
55%
Prediction components
Form (series winrate)44% vs 54%
Hero pool strength55% X3
Head-to-head0 – 1
Model total53% X3
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
IVY 47%X3 53%
The model gave 53% on X3 — the game was taken by IVY.
Game 2prediction correct
IVY 47%X3 53%
The model gave 53% on X3 — the game was taken by X3.
Game 3prediction correct
IVY 47%X3 53%
The model gave 53% on X3 — the game was taken by X3.
Model check result
Model favoriteX3 · 53%
Series resultX3 1:2
Series predictioncorrect
Accuracy by game2 of 3