Skip to content
How You Rank
Sign in
All ranking methods
Matrix Methods

Colley Matrix

scales globally

Builds one linear system from the whole schedule and solves it, so strength of schedule is accounted for without anyone weighting it by hand.

Solve CĀ·r = b (matrix system from W/L schedule)

Best at

Leagues where people play very different fixtures — it was designed for exactly that problem in college football.

Where it misleads

Wins and losses only; margins are ignored. Two-sided matches only, and the results can feel unintuitive because they fold in opponent strength.

How it works

The Colley Matrix method, developed by mathematician Wesley Colley, uses linear algebra to produce fair rankings from win/loss records, even when teams play vastly different schedules.

How it works: It constructs a matrix equation CĀ·r = b, where C captures the schedule and b captures the results. Solving this linear system produces ratings that account for strength of schedule without needing score margins. All teams start at 0.5 (equivalent to "average") and the system adjusts.

When to use it: Leagues or competitions where teams don't all play each other the same number of times. Originally developed for college football rankings (used in the BCS formula), it's ideal for any round-robin with incomplete or uneven schedules.

Watch out for: Computationally heavier than simple standings (requires matrix solve). Only uses win/loss data -- score margins are ignored. Only supports 1v1 or team matches. Results can be non-intuitive since they account for opponent strength indirectly.

Works well with

Also in Matrix Methods

Colley Matrix — How You Rank