The National Bureau of Economic Research recently published the paper “Predicting College Closures and Financial Distress.” Researchers used machine learning to predict institutional failure based on declining college-aged production, using data on college and university characteristics gathered from 2002 to 2023.
With the government expected to scrutinize federal investments more closely to minimize financial risk, federal agency involvement in this research could foreshadow federal use of predictive models to limit access to grants and loans for imperiled institutions.
A machine learning model that evaluates the financial health of institutions not only affects institutions, but also students, educators, and college communities.
Lessons learned from Santa Fe
Consider the case of the College of Santa Fe, which closed in 2009 during the recession after years of mounting expenses and insufficient revenue. Through a public-private partnership with the City of Santa Fe, Laureate Education purchased and reopened the school a year later as the for-profit Santa Fe University of Art and Design.
After continued financial challenges, declining enrollment, and a failed attempt to sell the institution to a Singapore-based education corporation, Santa Fe University of Art and Design closed in the spring of 2018.
The impact of any campus closure is widespread. The College of Santa Fe once educated many people in the capital city of New Mexico, a state with college attainment well below the national average. When the school closed, the municipal government still owed millions in debt from the purchase of the school’s property, 682 students and 75 full-time staff were left with uncertain futures, and the school faced lawsuits from students and families.
The power of machine learning in higher education
Clearly, educational institutions face very real, existential threats. However, there are enough people in America who have not yet completed a college credential to enable individual institutions to survive by building their enrollment with non-traditional students. Machine learning can help improve student recruitment and retention to support these efforts.
Higher education leaders should consider adopting predictive analytics, using data they already have and acting on the insights to increase enrollment and retention rates. Data utilization that is both proactive and innovative can help institutions get more students across the podium.
Effective change management can be difficult but is critical to success for such an initiative. To address the changes underway in the higher education sector, leadership should be willing to explore an innovative, best practices-based approach to data employed by successful peer institutions. Education leaders need to be strategic and sophisticated in their change management approach.
Conclusion
According to the recent report “Knocking at the College Door” from the Western Interstate Commission for Higher Education, there are more than enough potential students for higher education institutions.
Researchers found that if the matriculation rate – the rate at which high school graduates enroll in college – rises to 68% from the 2023 rate of 61%, this could offset a 10% decline in high school graduates, enabling schools to maintain current enrollment levels.
Faced with the perfect storm of low enrollment and retention, institutions are being pushed to the edge of a cliff, where calls for closure grow louder. Resultant’s Campus Analytics Engine and integrated change management offerings can help institutions avoid these cliffhangers, creating an early warning system that can identify recruiting and retention actions. This is critical to shoring up their enrollment as the nation adjusts to a smaller pool of 18 to 24 year olds.
With gaps in college attainment rates across many demographics, traditionally underrepresented groups can fill otherwise empty seats. This will require new strategies to recruit and retain students and support their success.
Educational institutions that adopt advanced analytics will be better equipped to navigate challenges and reduce the risk of school closures. We envision a future where data-driven decisions lead to well-matched student admissions and increased academic attainment.
Contact us to discuss how our Campus Analytics Engine can drive enrollment and student retention using data-driven insights
Talk to our team
Sources
