About The RPI

The Ratings Percentage Index (RPI) is a system used by the NCAA to evaluate teams for seeding and selection into the NCAA Tournament. The formula for this ranking system is published by the NCAA, and I've used it to generate the RPI ratings listed on this site.

From a statistical perspective, the RPI system does a lousy job of evaluating teams and/or predicting their future performance. It fails to take many variables into account, chiefly game score, game date and game location. As such, I think it makes for a weak ranking system, much less useful than mine, Jeff Sagarin's, or Kenneth Massey's, among others. I publish it because it's used by the NCAA, and for no other reason. As such, it's proved to be modestly correlated with teams' seedings for the Tournament. However, it often happens that teams which are highly overrated or underrated due to flaws in the RPI, are given vastly different seeds from what their RPI would suggest. More often than not, these teams have been seeded a lot closer to the TeamRankings power rating than their RPI. Thus I hope that both rankings can give people some insight as to where teams are likely to be seeded, along with certain unmeasurables, such as injuries and reputation.

If I've somehow missed a game, gotten the score wrong, gotten the location wrong, or done something else incorrectly, please email me.

Mike Greenfield is Senior Analytics Scientist at LinkedIn in Mountain View, California. He is a 2000 graduate of Stanford University, with a degree in Mathematical and Computational Science. He developed this system in 1997, and has been refining, improving, and expanding it ever since.