Department of Economics

2009 Data Mining

Home of Back-to-Back National Champions in Data Mining

The SAS Institute in Cary, NC announced on October 27 that SMU’s Data Mining team is the top data mining team in the nation in the 2009 SAS Data Mining Shootout co-sponsored by SAS, Dow, and Central Michigan University Research Corporation. 

The announcement was made at the 12th annual SAS Data Mining Conference at Caesars Palace in Las Vegas, Nevada.

The three students on the team are Michael Fulmer, Jingjing Ye and Steven Gregory.  They and their faculty sponsor, Economics Department Chair Tom Fomby, received all expense paid trips to Las Vegas to attend the conference and the award ceremony.

The other two top finishers were North Carolina State University and Oklahoma State University.  In total, 47 teams from universities and colleges across the country signed up for the competition while 28 provided a final submission for judging.

In this year’s competition the team members were asked to serve as data mining consultants to a fictitious company named American Energy Resources (AER).  They were asked to determine the top three   locations to build bio-fuel plants for processing a new bio-fuel called Energy Grass.  The problem set came with extensive U.S. county data for several years on the yields of Energy Grass, corn, wheat, and soybeans as well as many other variables including weather and soil characteristics within the same counties.  The data was used to build models to determine where Energy Grass can best be grown (and thus processed).    In short, AER’s processing plants needed to be located in those counties where Energy Grass yields are sufficiently high while, at the same time, yields of corn, wheat, and soybean are sufficiently low thus allowing the farmers to cover their opportunity costs of producing Energy Grass.  The students’ final report was to state their choices for the top three counties and top three states for locating the AER bio-fuel plants and to discuss in detail the methodologies they used in arriving at their choices.           

SMU’s Economics Department also fielded the national champion in last year’s competition.  Last year’s team members were Stefan Avdjiev, Manan Roy, and Jayjit Roy.  They investigated a complex scheduling problem involving a fictitious airline company attempting to maximize customer satisfaction at three airports by properly scheduling hotel rooms and rental cars for customers caught in air traffic delays and cancellations.  Using weather forecasts, among other variables, the teams were to build models to predict whether flights would be cancelled and, if so, pre-reserve a sufficient number of hotel and rental car accommodations for the stranded customers of the airline.  Each team was given information involving 750,000 arrivals and departures upon which to build their predictive models.  

  

 

SMU Economics Department Has One of the

Top 3 Data Mining Teams in the Nation!

 

The SAS Institute in Cary, NC announced on September 1, 2009 that SMU’s Data Mining team has placed as one of the top three Data Mining Teams in the Nation for the 2009 SAS Data Mining Shootout co-sponsored by SAS, Dow, and Central Michigan University Research Corporation.  The order of finish will be announced at the 12th annual SAS Data Mining Conference Tuesday morning, October 27, 2009 at Caesars Palace in Las Vegas, Nevada.  The three students on the team, Michael Fulmer, Jingjing Ye, and Steven Gregory, along with their faculty sponsor, Tom Fomby, will receive all expense paid trips to Las Vegas to attend the conference and the award ceremony on Oct. 27.  The other two top finishers are North Carolina State University and Oklahoma State University.  In total, 47 U.S. universities and colleges registered while 28 provided a final submission for judging.

SMU’s Economics Department fielded the National Champion in last year’s competition.  The team members were Stefan Avdjiev, Manan Roy, and Jayjit Roy.