About the model

TennisPredict estimates the probability that a player or pairing 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.

Singles vs doubles

Singles uses the standard one-on-one rating. Doubles is harder and more interesting: a pairing is modelled as the blend of its two members' individual doubles ratings plus a learned chemistry term — how that specific duo over- or under-performs the sum of its parts. New, unproven pairings are treated as more uncertain (wider rating deviation) so early predictions stay humble. Men's, women's and mixed doubles are rated on separate surfaces.

vs ATP/WTA rankings

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

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