LRMC is a college basketball ranking system designed to use only basic scoreboard data: which two teams played, whose court they played on, and what the margin of victory was.
LRMC stands for "Logistic Regression/Markov Chain", the two primary mathematical techniques that were a part of our system. We've subsequently added a Bayesian component as well.
We calculate three types of LRMC rankings:
- Bayesian LRMC rankings -- These LRMC rankings use full information about home court advantage and margin of victory, using an empirical Bayes model to estimate win probabilities.
- Classic LRMC rankings -- These LRMC rankings use full information about home court advantage and margin of victory, using a logistic regression model to estimate win probabilities.
- LRMC(0) -- Since the NCAA prefers to de-emphasize margin of victory so teams aren't encouraged to run up the score and players don't get focused on point spreads, we calculate a version of LRMC for them that doesn't take margin of victory into account. These LRMC(0) rankings are less accurate than Bayesian and Classic LRMC, but they're compatible with NCAA's mission and preferences.