One student got mostly A's and B's last semester—and just one C.
Another, a nursing student, aced the introductory nursing course but struggled in introductory math.
These students are probably fine, right?
These are some of the insights from a new approach that could "revolutionize the way student advising works," Joseph Treaster reports for the New York Times.
Increasingly, colleges are using predictive analytics to look for red flags to warn them which students may need additional academic support. Often, the indicators are surprising.
For example, faculty at Georgia State University's (GSU) nursing school used to believe that a student who struggled in "Conceptual Foundations in Nursing" probably wouldn't graduate. But after analyzing the data using EAB's Student Success Collaborative (SSC) platform, officials learned that introductory math was actually a much more important indicator of students' performance later in their academic careers.
"You could get a C or an A in that first nursing class and still be successful," according to Timothy M. Renick, vice provost at GSU. "But if you got a low grade in your math courses, by the time you were in your junior and senior years, you were doing very poorly."
Renick compares how predictive analytics work on campus to how similar algorithms work for Amazon. "When Amazon looks at all your choices of books and makes predictions that you'll like other books, it doesn't need to know why you'll like the third book," he told the Times. "Our big data doesn't need to know exactly why a student gets a bad grade. It just happens thousands and thousands of times. We're looking at a pattern."
Learn more: Predictive analytics helps colleges identify and scale student interventions
Administrators had a similar experience at Middle Tennessee State University (MTSU). Before introducing the SSC platform, advisors mostly focused on each student's grade point average. So a student who finishes a semester with one C might seem fine.
"But, really, he was at risk," explains Richard D. Sluder, vice provost for student success at MTSU.
Officials learned that a foundational history course was an important predictor of a student's future performance.
"History is a heavy reading course," Sluder says. So if a student struggles in that course, "it signifies a need for reading comprehension," he adds.
Both GSU and MTSU have made investments elsewhere on campus to support their use of predictive analytics, or in response to findings they discovered through the platform. But both institutions have also seen improvements in student retention and success. GSU's four-year graduation rate has risen five percentage points and its six-year graduation rate has risen six points. At MTSU, the freshman retention rate has risen five percentage points in just two years (Treaster, New York Times, 2/2).
Learn how an analytics-driven approach can help you graduate more students
Next in Today's Briefing
Empathy is not a virtue, psychologist argues