ESL One Fall 2021 · BO2
result vs prediction
SG e-sportsloss 1:1series probability
40%60%
probability at match start · final 1:1
Team Empireloss 1:1The 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.
SG e-sports
No games played over 6 months.
Team Empire
Hoodwinksignature
sayuw · 25 games
Invokersignature
kiyotaka · 19 games
Enchantressoften banned
VANSKOR · 17 games
Linasignature
kiyotaka · 12 games
Timbersawoften banned
Petushara · 11 games
Lunasignature
Smiling Knight · 10 games
Abaddonsignature
VANSKOR · 9 games
Clockwerksignature
sayuw · 7 games
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.
Lion
409 picks · 190 bans
Hoodwink
357 picks · 134 bans
Nyx Assassin
296 picks · 602 bans
Puck
283 picks · 620 bans
Dragon Knight
281 picks · 359 bans
Mars
281 picks · 470 bans
Winter Wyvern
270 picks · 236 bans
Lina
249 picks · 358 bans
Prediction components
Form (series winrate)53% vs 68%
Hero pool strength60% Team Empire
Head-to-head0 – 0
Model total60% Team Empire
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 correct20:35
SG e-sports 40%Team Empire 60%
The model gave 60% on Team Empire — the game was taken by Team Empire in 48:01.
Game 2prediction correct18:2
SG e-sports 40%Team Empire 60%
The model gave 60% on Team Empire — the game was taken by Team Empire in 24:46.
Model check result
Model favoriteTeam Empire · 60%
Accuracy by game2 of 2