Georgia Tech computer systems predicts NCAA Tournament Champ

7:55 PM, Mar 21, 2013   |    comments
Joel Sokol (Photo: Ga. Tech Media Relations)
  • Share
  • Print
  • - A A A +

MIDTOWN -- According to Georgia Tech's Logistic Regression/Markov Chain (LRMC) computerized college basketball ranking system, Florida will take the NCAA Basketball Championship.

Jason Maderer of Georgia Tech said the computerized model has chosen the men's basketball national champion in three of the last five years.

By using LRMW, Georgia Tech has determined that Florida, Louisville, Indiana and Gonzaga will likely play in the Final Four round in Atlanta. Florida and Gonzaga will be the teams going head to head to claim the title on Monday, April 8.

RELATED | Atlanta braces for March Madness

According to Maderer, it's the first time in the LRMC's 10-year history a team that isn't a number one seed is picked to win the tournament.

Joel Sokol oversees the project. He is an associate professor in Tech's School of Industrial & Systems Engineering (ISyE) - their research specialties include analyzing sports and applied operations research.

As the season is played, the LRMC uses scoreboard stats to create a weekly ranking of all 347 Division I NCAA teams. A math formula is used to evaluate every game and factors in the margin of victory and where each game is played. When the field of 68 was announced on Sunday, Sokol's team released its bracket.

Maderer said the team presented a paper last year that showed the LRMC has been the most accurate predictive ranking system over the last ten years. LRMC proved better than 80 others, including the NCAA's Ratings Performance Index (RPI).

"Our system combines the aspects of performance and strength of schedule by rewarding game performance differently according to the quality of each opponent," Sokol said. "Compared to something like RPI, LRMC is able to predict which team is better by taking the margins of victories and losses into account."

The LMRC identifies which team is most likely to win each game, with the exception of upsets. Maderer said that about 25 percent of NCAA tournament matchups end in upsets.

Not only does the LRMC predict tournament winners, it also helps dissolve belief in some myths of the sport. For example, there is not home court advantage for any team, and all home courts are about the same.

"The reason that you hear people say things like 'Duke is one of the toughest home courts - it's so hard to win there' isn't because of the court or the fans," Sokol said. "It's that Duke is usually such a good team. When you give them even a three- or four-point home court advantage on top of the skill advantage they usually have, it's hard to overcome."

Another false belief is that good teams know how to win close games.

"If the cliché was true, teams that won close games at home would have a significantly higher winning percentage in the road rematch than teams that lost close games at home," Sokol said.

But close home winners won about 35 percent of their road rematches. Close home losers won about 33 percent.

Sokol also used LRMC to explore the NCAA's consideration of expanding the tournament to include 96 teams. LRMC data showed that those dramatic upsets would drop by around five, potentially causing fans to lose interest.

Sokol is joined on the LRMC team by fellow ISyE Professors Paul Kvam and George Nemhauser, as well as Professor Mark Brown of City College, City University of New York.

MORE | How to get Final Four tickets

Most Watched Videos