By using a predictive analytics model, Middle Tennessee State University (MTSU) retained 390 students at risk of dropping out, Tara García Mathewson reports for Education Dive.
As a member of EAB's Student Success Collaborative, MTSU has access to a predictive model that identifies at-risk students, analytics capabilities to evaluate targeted campaigns, and a referral system for staff to coordinate student support.
MTSU is using its system to track pre-registration on a semester-by-semester basis, with persistence rates as a predictor of retention. The university also hired 47 new advisors, reducing the student-to-advisor ratio to a median of 260:1.
During the 2014-2015 school year, 390 additional MTSU students persisted from the fall to spring semester, generating an additional $1.5 million estimated revenue in tuition and fees. Now MTSU aims to boost its first-year freshman retention rate from 73.2% to 80%.
EAB Director Ed Venit points to 61 different targeted campaigns that have been used across the country to identify students with performance concerns, such as those with GPAs in the "murky middle" for their major or concentration.
While some have argued that predictive models make advisors' roles more rigid, Venit says that tracking data offers advisors another tool for understanding student performance.
"This is giving advisors more information when they work with students," Venit says. "We're taking data the advisor was looking at anyway and making it more accessible" (García Mathewson, Education Dive, 6/15).
Still curious? Read our full case study on MTSU
Like what you're reading?
Keep up with the latest by following EAB on LinkedIn.
Next in Today's Briefing
Heated workplace conversation? Here's how to cool things off.