?
arrow_backBack to match
European Pro League Season 32 · BO3
result vs prediction
Kalmychataloss 0:2
series probability
28%72%
probability at match start · final 0:2
Pipsqueak+4win 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.

Kalmychata

Dawnbreaker
Dawnbreakeroften banned
Ankou · 20 games
55%
Ringmaster
Ringmaster
raregods · 18 games
50%
Void Spirit
Void Spiritsignature
WoE · 18 games
61%
Queen of Pain
Queen of Painsignature
Ethereal · 16 games
63%
Sven
Svensignature
rincyq · 16 games
69%
Leshrac
Leshracsignature
Ethereal · 15 games
60%
Terrorblade
Terrorbladesignature
rincyq · 15 games
67%
Bounty Hunter
Bounty Huntersignature
raregods · 14 games
86%

Pipsqueak+4

Warlock
Warlock
Kidaro · 29 games
52%
Centaur Warrunner
Centaur Warrunnersignature
Palantimos · 24 games
67%
Mars
Marsoften banned
Nande · 19 games
58%
Batrider
Batridersignature
Kaori · 16 games
63%
Dragon Knight
Dragon Knightoften banned
xn丶e · 16 games
44%
Puck
Pucksignature
xn丶e · 16 games
69%
Jakiro
Jakirosignature
Kidaro · 15 games
67%
Storm Spirit
Storm Spiritoften banned
xn丶e · 15 games
40%
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.
Snapfire
Snapfire
740 picks · 350 bans
53%
Disruptor
Disruptor
605 picks · 640 bans
52%
Hoodwink
Hoodwink
530 picks · 278 bans
51%
Puck
Puck
435 picks · 1187 bans
49%
Mars
Mars
428 picks · 700 bans
52%
Dragon Knight
Dragon Knight
426 picks · 454 bans
50%
Tusk
Tusk
425 picks · 267 bans
50%
Jakiro
Jakiro
373 picks · 241 bans
46%
Prediction components
Form (series winrate)52% vs 59%
Hero pool strength53% Kalmychata
Head-to-head2 – 0
Model total72% Pipsqueak+4
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 correct33:13
Kalmychata 28%Pipsqueak+4 72%
The model gave 72% on Pipsqueak+4 — the game was taken by Pipsqueak+4 in 28:38.
Game 2prediction correct43:24
Kalmychata 28%Pipsqueak+4 72%
The model gave 72% on Pipsqueak+4 — the game was taken by Pipsqueak+4 in 40:38.
Model check result
Model favoritePipsqueak+4 · 72%
Series resultPipsqueak+4 0:2
Series predictioncorrect
Accuracy by game2 of 2