?
arrow_backBack to match
European Pro League Season 27 · BO3
result vs prediction
eSpoiledloss 0:2
series probability
56%44%
probability at match start · final 0:2
Level UPwin 2:0
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.

eSpoiled

Windranger
Windranger
Wein · 8 games
25%
Tusk
Tusk
Wein · 7 games
57%
Sven
Sven
ssnovv1 · 5 games
40%
Drow Ranger
Drow Rangeroften banned
ssnovv1 · 4 games
50%
Terrorblade
Terrorbladeoften banned
ssnovv1 · 4 games
25%
Ursa
Ursaoften banned
ssnovv1 · 4 games
50%
Naga Siren
Naga Sirenoften banned
asdekor_r · 3 games
67%
Oracle
Oracleoften banned
asdekor_r · 3 games
33%

Level UP

Dark Seer
Dark Seeroften banned
Ankou · 5 games
40%
Puck
Puckoften banned
MaTson · 5 games
0%
Earthshaker
Earthshaker
xsvampire · 4 games
50%
Invoker
Invokeroften banned
MaTson · 4 games
50%
Leshrac
Leshrac
Atoufix · 4 games
25%
Magnus
Magnusoften banned
4IVAN · 4 games
50%
Bristleback
Bristlebackoften banned
Gunnar · 3 games
33%
Queen of Pain
Queen of Painoften banned
MaTson · 3 games
33%
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
565 picks · 637 bans
50%
Ringmaster
Ringmaster
490 picks · 248 bans
52%
Jakiro
Jakiro
464 picks · 424 bans
49%
Terrorblade
Terrorblade
400 picks · 854 bans
47%
Shadow Shaman
Shadow Shaman
383 picks · 436 bans
57%
Storm Spirit
Storm Spirit
378 picks · 564 bans
51%
Tusk
Tusk
374 picks · 327 bans
49%
Ancient Apparition
Ancient Apparition
356 picks · 834 bans
54%
Prediction components
Form (series winrate)50% vs 27%
Hero pool strength53% eSpoiled
Head-to-head0 – 0
Model total56% eSpoiled
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
eSpoiled 56%Level UP 44%
The model gave 56% on eSpoiled — the game was taken by Level UP.
Game 2prediction missed
eSpoiled 56%Level UP 44%
The model gave 56% on eSpoiled — the game was taken by Level UP.
Model check result
Model favoriteeSpoiled · 56%
Series resultLevel UP 0:2
Series predictionmissed
Accuracy by game0 of 2