?
arrow_backBack to match
CIS Battle 4 · BO3
result vs prediction
Most Wantedloss 0:2
series probability
50%50%
probability at match start · final 0:2
Kalmychatawin 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.

Most Wanted

Tusk
Tusksignature
Ponlo · 23 games
70%
Ringmaster
Ringmastersignature
Ponlo · 18 games
67%
Shadow Demon
Shadow Demonsignature
Ponlo · 18 games
78%
Mars
Marssignature
fortniteMan · 16 games
75%
Nature's Prophet
Nature's Prophetsignature
niche · 16 games
81%
Bristleback
Bristlebacksignature
fortniteMan · 15 games
73%
Ember Spirit
Ember Spiritsignature
niche · 15 games
80%
Marci
Marcisignature
fortniteMan · 15 games
80%

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%
Leshrac
Leshracsignature
Ethereal · 15 games
60%
Terrorblade
Terrorbladesignature
rincyq · 15 games
67%
Bounty Hunter
Bounty Huntersignature
raregods · 14 games
86%
Dazzle
Dazzlesignature
raregods · 14 games
71%
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
652 picks · 279 bans
51%
Jakiro
Jakiro
613 picks · 597 bans
49%
Dragon Knight
Dragon Knight
565 picks · 724 bans
50%
Hoodwink
Hoodwink
542 picks · 265 bans
52%
Tusk
Tusk
538 picks · 324 bans
50%
Centaur Warrunner
Centaur Warrunner
492 picks · 576 bans
54%
Disruptor
Disruptor
482 picks · 456 bans
51%
Mars
Mars
469 picks · 663 bans
50%
Prediction components
Form (series winrate)69% vs 49%
Hero pool strength58% Most Wanted
Head-to-head1 – 1
Model total50% Most Wanted
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 missed10:32
Most Wanted 50%Kalmychata 50%
The model gave 50% on Most Wanted — the game was taken by Kalmychata in 22:46.
Game 2prediction missed11:19
Most Wanted 50%Kalmychata 50%
The model gave 50% on Most Wanted — the game was taken by Kalmychata in 23:41.
Model check result
Model favoriteMost Wanted · 50%
Series resultKalmychata 0:2
Series predictionmissed
Accuracy by game0 of 2