Where he stands
Kevin Lee is 9-7 across 16 fights on our tape. He's on a 3-fight losing run. Our rating has him at 1572 — it moves with every result and weights who he beat, so a win over a ranked opponent counts for far more than one over a debutant. A record on its own says very little in this sport — two fighters at 12-3 can have faced completely different opposition, which is exactly the gap the rating is built to close.
He wants the fight on the mat
Kevin lands 3.1 takedowns per 15 minutes and threatens 0.7 submissions in the same span. That's the profile the model reads first, because grappling decides where a fight happens and where it happens decides most of the rest. His matchups turn on one number more than any other — the opponent's takedown defense. Against 85%-plus defense the same fighter looks ordinary; against a striker who can't stop it he looks unbeatable.
How the model reads him
Kevin's rating updates after every result and weights the quality of the opponent. Against a specific opponent it becomes a win probability, adjusted for the stylistic matchup — striking output against absorption, takedown rate against takedown defense — plus age and layoff. The weighting is ours; the output is published on the fight board and graded.
What we'd flag
The tape starts in 2015 and covers UFC and Contender Series only, so career records elsewhere aren't reflected. Beyond that: MMA has the highest single-event variance of anything we model, and no rating survives contact with a flush shot.