What Predictive Models Can and Can’t Tell You about Student Success

One of the best things about predictive data modeling is that an institution can find at-risk students that may not yet have surfaced from standard red-flags like prior academic performance – and be able to provide them with additional support.

The problem is that there are thousands of student success factors even the best predictive models don’t have access to.

The takeaway? Let’s use all the data points we have in order to create better models, identify at-risk students, and provide them with better support. But let’s also understand that predictive modeling with a limited data set is not a perfect science.

Have an Amazon Alexa-compatible product? Subscribe to our Enrollment Growth Briefing.

Eric Olsen

As AVP of Marketing, Eric brings more than a decade of award-winning creative brand development, marketing analytics and higher education experience to Helix Education. Eric is a graduate of Bradley University and earned his MBA at Lewis University.