Every registered result updates your play level. Your level goes up when you perform better than expected.
We use your level to set up balanced matches. Matches against opponents of similar strength are the most fun, with long rallies and close results.
After every match, your level is adjusted based on how you performed compared to what was expected. If you do better than expected, your level goes up. If you do worse, it goes down.
For example, if you are a 3-star player and you beat another 3-star player, your level goes up and your opponent's level goes down.
Losing doesn't always mean your level drops. If you are a 3-star player and narrowly lose to a 4-star player, you did better than expected, so your level goes up and your opponent's level goes down.
Winning doesn't always mean your level rises, either. If you are a 3-star player and only narrowly beat a 2-star player, your level goes down and your opponent's level goes up. Against a weaker opponent, you need to win by a clear margin to keep or raise your level.
Your initial level
New players select their own play level, and the first match is based on this self-assessment. Levels are corrected very quickly using match results — typically within one or two matches — so it's fine if your estimate is a bit off.
Team results and your own level
Doubles results always move your personal level too. When a pair has no team level yet, we build one from both players' levels. After the match, the team's move is passed back to each player - a long way if your level is still uncertain, barely at all if it is well established.
Category neutral
Our play levels are 'gender-neutral', meaning a match between a woman and a man should be balanced if their level is the same. We use different level descriptions (e.g. Beginner, Intermediate, Advanced) for men, women and junior players so that levels are accurately described while maintaining a unified play level.
Yearly corrections
At the start of each year, your level may change even if you haven't played any matches. To keep the system fair and meaningful, we analyze the spread of all player ratings (their statistical distribution and standard deviation). If the overall scale has drifted during the year, we adjust levels for all players at once, while keeping the relative order exactly the same.
For nerds
Bayesian inference meets racket sports: we model player skill as a dynamic normal distribution, continuously updated from match outcomes. Z-scores, star ratings, and vanishingly rare 10-star outliers — the math is worth a look.