November 1, 2010
A team of Ph.D. students in the Industrial Engineering Department at Oklahoma State University edged out the SMU Data Mining team to win first place in the national 2010 SAS Data Mining Shootout competition.
The order of finish of the competition was announced on October 25 at the SAS Data Mining Conference held at Caesar’s Palace in Las Vegas, Nevada.
The SMU team made up of Subhojit Das, Greg Johnson and Jacob Williamson finished second in the competition. Das and Johnson are third year students in the Economics Ph.D. program and Williamson is a second year Applied M.A. student in the Economics Department. The faculty sponsor was Economics Professor Tom Fomby.
A team of Ph.D. students from the Information Systems and Quantitative Sciences (ISQS) Department at Texas Tech University finished third.
The problem statement of the 2010 SAS Data Mining competition was posted to all U.S. universities in February of this year. All solutions were due by July 19, 2010.
Proposed solutions involved analyzing the medical, demographic, and behavioral data of 50,788 individuals, some of whom had diabetes. The task was to determine the economic benefit of reducing the Body Mass Indices (BMIs) of a selected number of individuals by 10% and to determine the cost savings that would accrue to the Federal Government’s Medicare and Medicaid programs, as well as to the economy as a whole, from the implementation of the proposed BMI reduction program.
Sixty applications were received from Colleges and Universities across the nation with 17 of the 60 qualifying for final submission. The completion was judged on the applicability and accuracy of the proposed solution algorithm and the quality of the submitted report detailing the results produced by the solution algorithm.
This is the third year in a row that SMU’s Economics Department has fielded one of the top three Data Mining teams in the nation in the annual SAS Data Mining Shootout competition. The previous two SMU teams finished as National Champions.
Fomby is already in the process of putting together another team to participate in the 2011 SAS Data Mining Shootout. Winners of that competition will be announced at the 2011 SAS Analytics conference to be held in Orlando, Florida in October of 2011.
# # #