?
arrow_backBack to match
European Pro League Season 28 · BO3
result vs prediction
Kalmychataloss 1:2
series probability
33%67%
probability at match start · final 1:2
4Pirateswin 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.

Kalmychata

Sven
Svensignature
rincyq · 9 games
67%
Death Prophet
Death Prophetoften banned
xn丶e · 8 games
50%
Ringmaster
Ringmaster
not me · 7 games
57%
Terrorblade
Terrorbladesignature
rincyq · 7 games
71%
Mars
Mars
fortniteMan · 6 games
50%
Shadow Fiend
Shadow Fiendsignature
Mirage · 6 games
67%
Axe
Axeoften banned
meLes · 5 games
60%
Chaos Knight
Chaos Knight
Ponlo · 5 games
40%

4Pirates

Shadow Shaman
Shadow Shamanoften banned
PERDAN4IK · 29 games
55%
Pangolier
Pangolieroften banned
NattyNarwhal · 27 games
48%
Sniper
Snipersignature
NattyNarwhal · 21 game
67%
Nature's Prophet
Nature's Prophetsignature
Otaker · 20 games
70%
Dawnbreaker
Dawnbreakersignature
Otaker · 18 games
78%
Tiny
Tinyoften banned
NattyNarwhal · 18 games
56%
Tusk
Tusksignature
PERDAN4IK · 18 games
61%
Beastmaster
Beastmastersignature
Otaker · 17 games
76%
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 · 535 bans
55%
Tiny
Tiny
413 picks · 430 bans
48%
Tusk
Tusk
351 picks · 356 bans
49%
Pangolier
Pangolier
339 picks · 505 bans
50%
Terrorblade
Terrorblade
321 picks · 700 bans
46%
Ringmaster
Ringmaster
300 picks · 174 bans
52%
Storm Spirit
Storm Spirit
296 picks · 434 bans
48%
Dark Willow
Dark Willow
295 picks · 189 bans
53%
Prediction components
Form (series winrate)62% vs 66%
Hero pool strength54% 4Pirates
Head-to-head2 – 0
Model total67% 4Pirates
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
Kalmychata 33%4Pirates 67%
The model gave 67% on 4Pirates — the game was taken by 4Pirates.
Game 2prediction missed
Kalmychata 33%4Pirates 67%
The model gave 67% on 4Pirates — the game was taken by Kalmychata.
Game 3prediction correct
Kalmychata 33%4Pirates 67%
The model gave 67% on 4Pirates — the game was taken by 4Pirates.
Model check result
Model favorite4Pirates · 67%
Series result4Pirates 1:2
Series predictioncorrect
Accuracy by game2 of 3