While Duke was crowned the victor in the NCAA men's basketball national championship this month, another big winner emerged: the Georgia Tech LRMC method for predicting NCAA tournament outcomes.  

The new Bayesian LRMC method – an updated version of the previous system – correctly predicted the winner of more games during this year's tournament than all other ranking systems tracked on BCS computer ranker Ken Massey's website, masseyratings.com, which analyzes predictions for various sporting events.

Bayesian LRMC finished three full games ahead of the field, which included well-known rankings such as the Associated Press and USA Today polls, the NCAA's Ratings Percentage Index, Pomeroy, Sagarin and Massey's own computer ranking methods.  Bayesian LRMC was the only ranking to correctly predict the winner of more than 50 games.

In addition to Bayesian LRMC's first place finish, the original LRMC method finished in a three-way tie for second place with 48 correct predictions.  A correct prediction was defined as the winner of a game being ranked higher than the game's loser.

This is the second recent success for the system. In 2008, the LRMC correctly predicted the winner of every game in the final three rounds of the NCAA tournament before the tournament started.

The LRMC method was first developed by Professors Paul Kvam and Joel Sokol at Georgia Tech's H. Milton Stewart School of Industrial and Systems Engineering (ISyE).  The LRMC team has since expanded to include ISyE professor George Nemhauser and City College of New York mathematics professor Mark Brown.

A mathematical description of Bayesian LRMC is forthcoming in the Journal of Quantitative Analysis in Sports.