Associate Director of Data Analysis and Specialized Recruitment
Alabama posts gains with recruiting, retention
Data mining students help the University of Alabama attract and keep students
On a recent stroll across the University of Alabama campus, Cali Davis, the school's Associate Director of Data Analysis and Specialized Recruitment, was struck by the number of students she saw. Campus is more crowded these days – enrollment is up by 11 percent in the last three years, she notes with satisfaction. That's a sure sign that, with help from SAS, the school's recruitment and retention work is paying off.
Meanwhile, students in a data mining certificate course at the Culverhouse College of Commerce and Business Administration put what they’re learning in the classroom to real-world use in support of Davis’ work.
More students mean the need for more infrastructure. Davis explains. “UA has completed the third phase of a Science and Engineering Complex, with the fourth phase under construction,’’ explains Davis. More students also translate into more dollars for the community because when parents come to visit, they inevitably take their children shopping.”
In fact, the loss of 100 students can have an overall economic impact of losing $3 million over four years, Davis and Michael Hardin, Dean of the Culverhouse College of Commerce and Business Administration, say.
"We are one of the first universities to use data mining for retention and all the way through the cycle to include intervention as well as recruitment. I don't know how we would have done this without help from SAS."
Keeping students coming back
The University of Alabama’s partnership of enrollment strategy and the classroom was born a few years ago when Hardin’s data mining students began working with the school’s enrollment office to identify freshmen at risk of dropping out. By looking at data points such as college entrance test scores, grade-point averages and demographic features like single-parenthood, university staff had reason to intervene early enough to prevent students from dropping out.
“Our challenge was to use university records to routinely recognize students who might be having problems and take steps to prevent them from leaving,” Hardin says. “With SAS, we were able to take existing data and identify students on a routine basis instead of creating a bunch of highly specialized measures and adding significant data collection costs.”
The university used techniques such as logistic regression, decision trees and neural networks to pinpoint freshmen most at risk of dropping out. “Now we’re providing personalized, individual contact that will help students connect to the university and return to Alabama,” Hardin says. “High-risk freshmen meet with academic advisors who stay in contact with the freshmen to make sure they are adjusting successfully.”
The work with high-risk freshman was so successful that Davis has now asked Hardin's students to look at all incoming freshmen and even new transfer students. "Having seen such amazing results for at-risk students, we decided to do this for all U. of Alabama students," says Davis, explaining that some students don't encounter academic trouble until later in their college careers, and some well-prepared freshman are also at risk. "Trying to identify risk factors prior to enrollment can help us recruit students that have a higher likelihood to persist and graduate," Davis says.
Attracting the best, the brightest
The school also relies on SAS for predictive analytics to find out which high school students are most likely to want to attend the University of Alabama. Davis can then share the results of her work with recruiters who live in states outside of Alabama where significant numbers of prospects reside.
Davis captures data on college choice preference, financial aid and scholarship awards, ACT and SAT scores, and on in-state or out-of-state residency status. This additional data helps Davis segment students in a variety of ways, including by state or region, so that the school can find out how best to market itself in a particular area. Focus-group testing helps confirm what Davis’ analytics with SAS reveal.
“As a result of admissions’ efforts – and with help from SAS – we’re seeing our recruitment and retention numbers improving,” Davis says, “and we’re seeing an increase in the quality of our students in terms of their high school grade-point averages and ACT/SAT scores.” As recruitment and retention improve, so does the university's financial bottom line. By increasing revenues, the University of Alabama can continue to improve educational and quality-of-life components that will, in turn, further help the school to attract and retain the best and brightest students, Hardin says.
"We are one of the first universities to use data mining for retention and all the way through the cycle to include intervention as well as recruitment," he adds. "I don't know how we would have done this without help from SAS."
Recruit and retain the best and brightest students.
SAS provides predictive analytics that help the university intervene before at-risk students drop out, and SAS helps identify high school students who are most likely to be interested in enrolling.
Increased revenue through successful recruitment and retention helps fund capital expenses and other projects that will, in turn, help attract more students.