?
European Pro League Season 28 · BO3
result vs prediction
TNL DOTAwin 2:1
series probability
48%52%
probability at match start · final 2:1
Nemiga Gamingloss 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.

TNL DOTA

Dark Willow
Dark Willowsignature
Fernans · 15 games
60%
Shadow Fiend
Shadow Fiendoften banned
dualrazee · 15 games
47%
Tusk
Tuskoften banned
Fernans · 14 games
36%
Kunkka
Kunkkaoften banned
dualrazee · 11 games
45%
Pangolier
Pangoliersignature
Norma · 11 games
64%
Undying
Undyingoften banned
flacko · 9 games
44%
Batrider
Batridersignature
dualrazee · 8 games
75%
Dark Seer
Dark Seersignature
Norma · 8 games
75%

Nemiga Gaming

Jakiro
Jakiro
monodrama · 14 games
29%
Centaur Warrunner
Centaur Warrunnersignature
Covisnine · 9 games
67%
Tiny
Tinyoften banned
bashka · 9 games
11%
Windranger
Windranger
xsvampire · 8 games
25%
Dragon Knight
Dragon Knightoften banned
young G · 7 games
43%
Sven
Svenoften banned
bashka · 7 games
57%
Pangolier
Pangolieroften banned
Covisnine · 6 games
33%
Sand King
Sand Kingoften banned
спортик · 6 games
0%
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
415 picks · 430 bans
48%
Tusk
Tusk
352 picks · 356 bans
49%
Pangolier
Pangolier
340 picks · 505 bans
50%
Terrorblade
Terrorblade
322 picks · 700 bans
47%
Ringmaster
Ringmaster
302 picks · 175 bans
52%
Storm Spirit
Storm Spirit
297 picks · 435 bans
49%
Dark Willow
Dark Willow
295 picks · 189 bans
53%
Prediction components
Form (series winrate)52% vs 52%
Hero pool strength61% TNL DOTA
Head-to-head2 – 0
Model total52% Nemiga Gaming
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
TNL DOTA 48%Nemiga Gaming 52%
The model gave 52% on Nemiga Gaming — the game was taken by TNL DOTA.
Game 2prediction correct
TNL DOTA 48%Nemiga Gaming 52%
The model gave 52% on Nemiga Gaming — the game was taken by Nemiga Gaming.
Game 3prediction missed
TNL DOTA 48%Nemiga Gaming 52%
The model gave 52% on Nemiga Gaming — the game was taken by TNL DOTA.
Model check result
Model favoriteNemiga Gaming · 52%
Series resultTNL DOTA 2:1
Series predictionmissed
Accuracy by game1 of 3