The rankings are a relative look at what peer teams think of each other.  In many ways this relative ranking is similar to other  opponent, or opponent’s opponents ranking/rating systems.  However the granularity of the comparison is not solely based upon margin of victory. The margins of victory are sorted into bins so that a particular team can “judge” its opponents.  It removes the pure linear, or even logarithmic relationship of margin of victory.  The relative relationships per team do NOT consider the team that is “judging.” Once all of the relative relationships per team are computed, an iterative computation of rankings is calculated until it is stable.

The repeat-ability of these relationships (final rankings) is very consistent. This is important because they are computed from scratch (random starts) every day.

Credit: Massey’s Ratings for the game data.