Copeland Score
For each opponent, work out who leads the series overall: +1 if you do, -1 if they do. Sum across everyone.
+1 per opponent beaten overall, -1 per opponent who beats you
Best at
Round-robin settings with plenty of repeated matchups, where the pairwise picture is complete.
Where it misleads
Sparse data produces ties and noise — a single meeting decides a whole pairing.
How it works
Copeland Score is inspired by social choice theory. For each pair of players, determine who has the winning record. You get +1 for each opponent you beat overall, -1 for each opponent who beats you, and 0 for ties.
How it works: Compare your overall record against every other player. If you've beaten Player X more times than they've beaten you, that's +1. If they lead, it's -1. Sum all pairwise results. The maximum score equals the number of opponents.
When to use it: When you want a method grounded in mathematical theory that considers the full landscape of matchups. It's particularly good at identifying the "true" best player in a round-robin style setting.
Watch out for: Requires sufficient shared matches between players for meaningful pairwise comparisons. Can produce many ties in sparse data. Better with many matches between the same players.