Skip to main content
Educational analyticsNot betting advice · research use only.
GameTime Picks
Today · Nov 1 · 17 eventsGames under wayLatest results· Oct 31
← Fight card

Bout 4 of 14

Wellington Turman vs Seokhyeon Ko

Sat, Nov 7, 8:00 PM ET · Welterweight · 3 rounds · UFC Fight Night: Cortes Acosta vs. Walker · Meta APEX

Fight history: Wellington Turman · Seokhyeon Ko

Simulation story

6 chapters · read from the published artifact
Skip to the report ↓
› 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.

Wellington Turman vs Seokhyeon Ko

Welterweight, 3 rounds on UFC Fight Night: Cortes Acosta vs. Walker. The model read both fighters' histories.

model ufc-fight-model@e657fc40b64dno run count recordedproduced Nov 1, 1:21 PM ET
Winner

Who the model expects to win

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

Wellington TurmanWellington Turman18-8-0
vs
Seokhyeon KoSeokhyeon Ko13-3-0
Model pickSeokhyeon Ko · 54.4%Decision 54.5% · Ends in round 3 or later 61.9%
18-8-0Record13-3-0
9Tracked bouts3
45.6%Win chance54.4%

From the tracked records (a summary, not the model's reasoning): Seokhyeon Ko has won 2 of 3 tracked bouts (67%) to Turman's 3 of 9 (33%). The model's method read makes a decision more likely than not (55%).

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 / TKO26.2%
Submission19.3%
Decision54.5%
Round

How far it goes

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

23
R1
15
R2
62
R3+
Ends in round 1
23.4%
Ends in round 2
14.6%
Ends in round 3 or later
61.9%
Goes the distance
54.5%

“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.

Wellington Turman
18-8-0
Tracked record

2-3 in the last 5 tracked bouts. 1 of 3 wins came by finish (33%); 5 of 9 tracked fights reached the judges (56%).

Strengths · weaknesses
− 67% of tracked bouts are losses (6 of 9)
Last 5 tracked
LJared GoodenSubmission R2
LRandy BrownDecision R3
LAndre PetroskiDecision R3
WMisha CirkunovSubmission R2
WSam AlveyDecision R3
Seokhyeon Ko
13-3-0
Tracked record

2-1 in the last 3 tracked bouts. 0 of 2 wins came by finish (0%); 3 of 3 tracked fights reached the judges (100%).

Not established
? Only 3 tracked bouts — too few to call a strength or weakness (needs 5)
? Only 1 tracked loss — too few to say how fights are lost; absence of data, not absence of weakness
Last 3 tracked
LJean-Paul LebosnoyaniDecision R3
WPhil RoweDecision R3
WOban ElliottDecision R3
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 50.0% · 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

Generated

Technical detailsModel fingerprint and the fight corpus it was fitted on.
model ufc-fight-model@e657fc40b64d
corpus 8,642 fights · 1994-03-11 to 2026-08-08 · scrape_ufc_stats (GPL-3.0)

Educational and paper-only — not betting advice.

More

Other bouts on this card