acm-header
Sign In

Communications of the ACM

ACM TechNews

Georgia Tech Computer System Predicts Ncaa Basketball Champion


View as: Print Mobile App Share:
Tipoff, the opening play of a basketball game.

A computerized college basketball ranking system puts the University of Florida on top in this year's NCAA tournament.

Credit: D. Myles Cullen/Wikimedia Commons

Georgia Tech’s Logistic Regression/Markov Chain (LRMC) computerized college basketball ranking system predicts the University of Florida will be the winner of this year's NCAA men's college basketball tournament.

LRMC predicts that Florida, Louisville, Indiana, and Gonzaga are the teams most likely to advance to the Final Four, with Florida and Gonzaga playing for the championship.

During the season, LRMC uses scoreboard data to create a weekly ranking of all 347 Division I NCAA teams. The computer system analyzes every game and factors in the margin of victory and where each game is played.

"Our system combines the aspects of performance and strength of schedule by rewarding game performance differently according to the quality of each opponent," says Georgia Tech professor Joel Sokol.

Last year, the LRMC team presented a paper that shows LRMC has been the most accurate predictive ranking system over the last 10 years, outperforming more than 80 others, including the NCAA’s Ratings Performance Index (RPI).

"Compared to something like RPI, LRMC is able to predict which team is better by taking the margins of victories and losses into account," Sokol says.

From Georgia Tech News
View Full Article

 

Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account