Today · Oct 18 · 17 events Games under way Settled· Oct 15

Bout 4 of 13

Kyle Daukaus vs Marc-Andre Barriault

Sat, Oct 17, 8:00 PM ET · Middleweight · 3 rounds · UFC Fight Night: Buckley vs. Malott · Rogers Place

Started · not saveable

Simulation story

6 chapters · read from the published artifact

› Loading the matchup model› Reading the outcome distribution› Preparing the score scenariosPress Play to step through what the model expects, chapter by chapter, or read the report below.

Kyle Daukaus vs Marc-Andre Barriault

Middleweight, 3 rounds on UFC Fight Night: Buckley vs. Malott. The model read both fighters' histories.

Winner

Who the model expects to win

Probabilities over the two fighters, from the head that was evaluated on its own preregistered bar.

Kyle Daukaus17-5-0

Marc-Andre Barriault17-11-0

Model pickKyle Daukaus · 58.1%Decision · round 3 or later (46%)

17-5-0Record17-11-0

9Tracked bouts16

58.1%Win chance41.9%

From the tracked records (a summary, not the model's reasoning): Kyle Daukaus has finished 3 of 4 wins (75%). The model's method read has a decision as the most likely of three endings (40%), short of a majority.

Method

How it ends

Read among fights that end with a winner — a draw or no-contest sits outside this sample, so the three add to 100%.

KO / TKO37.4%

Submission22.4%

Decision40.3%

Round

How far it goes

R3+ carries every fight that reaches the judges as well as every round-3-or-later finish.

R3+

Round 1

34.4%

Round 2

19.1%

Round 3 or later

46.5%

Goes the distance

40.3%

“Goes the distance” is the method head’s decision probability, not a separate model — so it cannot disagree with the bar above it.

The fighters

What the corpus knows about each of them

Tracked bouts only — a fight outside the corpus is not counted, and a thin record says so.

Kyle Daukaus

17-5-0

Tracked record

2-3 in the last 5 tracked bouts. 3 of 4 wins came by finish (75%); 3 of 9 tracked fights reached the judges (33%).

Strengths · weaknesses

− 56% of tracked bouts are losses (5 of 9)

Tendencies

· Most wins come inside the distance — 3 of 4, mostly by submission (1 KO/TKO, 2 submission)

· Most losses come inside the distance — 3 of 5 (3 KO/TKO, 0 submission)

Last 5 tracked

LBo NickalKO / TKO R1

WGerald MeerschaertSubmission R1

WMichel PereiraKO / TKO R1

LEryk AndersKO / TKO R2

LRoman DolidzeKO / TKO R1

Marc-Andre Barriault

17-11-0

Tracked record

1-4 in the last 5 tracked bouts. 4 of 6 wins came by finish (67%); 8 of 16 tracked fights reached the judges (50%).

Strengths · weaknesses

− 63% of tracked bouts are losses (10 of 16)

Tendencies

· Most wins come inside the distance — 4 of 6, mostly by KO/TKO (3 KO/TKO, 1 submission)

Last 5 tracked

LMichal OleksiejczukDecision R3

LShara MagomedovDecision R3

WBruno SilvaKO / TKO R1

LDustin StoltzfusKO / TKO R1

LJoe PyferKO / TKO R1

Method

Where these numbers come from

Three separate heads — winner, method and round — each fitted on a corpus of tracked UFC fights and each tested on past fights it never trained on before it was published. This is an experimental model: winner forecasts are graded on every new card, method and round are not yet graded, and it has not been shown to have an edge over the market.

Winner 60.6% accurate over 3,557 held-out fights · baseline 50% · log loss 0.6615 against 0.6931

Method 52.7% accurate over 3,557 held-out fights · baseline 46.7% · log loss 0.9692 against 1.0255

Round 60.6% accurate over 3,557 held-out fights · baseline 55.3% · log loss 0.9148 against 0.9549

model ufc-fight-model@e657fc40b64d

corpus 8,642 fights · 1994-03-11 to 2026-08-08 · scrape_ufc_stats (GPL-3.0)

generated Oct 17, 10:02 AM ET

Educational and paper-only — not betting advice.

Simulation story

Kyle Daukaus vs Marc-Andre Barriault

Who the model expects to win

How it ends

How far it goes

What the corpus knows about each of them

Where these numbers come from

Other bouts on this card