Over the years, LRMC has correctly predicted the outcomes of more NCAA tournament games than competing ranking systems. The graph below shows LRMC's relative accuracy compared to over 75 other rankings (most data is from Ken Massey's comparison site). We've highlighted some well-known rankings for comparison.
LRMC Classic has been available for that entire time. We went back and ran our Bayesian algorithm on all those years of data to get the results in the figure above, but since we've only been releasing our Bayesian LRMC rankings since 2010 we also checked to make sure its success wasn't a fluke of past data. Here's how the results stack up since its first release in 2010:
The data used to make these comparisons is available here. For a paper summarizing several ways of comparing the data, see our most recent paper listed here.
