About the model

UFCPredict estimates the probability that a competitor wins a given match. It is built on the same proven pipeline as our sumo and snooker sites: a temperature-scaled ELO rating blended with Glicko-2 (which tracks how certain each rating is), with a gradient-boosted correction layer planned once enough match data accumulates.

Head to head

Each competitor carries an ELO+Glicko rating per surface. A matchup probability comes straight from the rating gap, temperature-scaled so favourites aren't over-trusted. Newer competitors have a wider rating deviation, so early predictions stay humble until results accumulate.

vs consensus

We ingest consensus as both a model feature and a public benchmark. The performance page will show our calibration against consensus-implied odds.

These are model probabilities for entertainment and analysis, not betting advice.