Data Analytics

University of Oklahoma Taps AI to Strengthen Student Retention Rates

Share this post:

Graduating from a four-year college in four years should be an achievable goal, but only just over 40 percent of students are able to reach this milestone. A critical driver for achieving on-time graduation is first-year retention. But for public institutions, like the University of Oklahoma (OU), the national average of full-time, first-time students who started school in fall 2013 returned in fall 2014 is just 64.2 percent, according to a report from ACT, which administers the national college admissions examination.

While reasons for attrition vary, we often hear from our OU freshmen when they decide not to return for sophomore year that the time wasn’t right for school. This limited insight initiated a recent retention project to learn more about our student population, their happiness and ultimate success.

With the help of IBM Watson technology, we set out to achieve a mandate to hit a 92 percent freshman retention rate over the next few years. Together with IBM, our data scientists and OU’s IT division developed a system to identify students likely needing additional services to persist into their second year. Traditionally, the university has relied on such structured data as SAT/ACT scores, GPA and math proficiency to determine the risk of student dropout. With artificial intelligence we are leveraging unstructured information such as student application essays as part of the retention analyses to better understand context for our individual students.

IBM’s Watson sentiment analysis capabilities and open APIs, such as tone analyzer, personality insights and natural language classifier, introduce a new level of personalization to the student experience. Identifying students who are a potential retention risk before they start their first semester allows OU to proactively provide access to the extra services they need, including tutoring, advising, and/or financial aid counseling.

With advanced analytics and artificial intelligence, we can connect the insights to immediate actions for instant results. This program with IBM played an important role in helping our first-year retention rate climb from 86.1 percent in fall 2015 to an OU record 92.1 percent in fall 2017.

By understanding the challenges OU students are facing, we can assist them as individuals in areas in which they might be struggling. We want our students to feel that they don’t have to go it alone, and that we have an abundance of tools, services and support on campus to ensure they have a clear path and comprehensive plan toward graduation.

Ultimately this effort and these strategies, empowered by IBM technology, accrue to the benefit of students and student service.  We are able to serve students better than ever before. This summer CIO Magazine recognized the retention initiative the University of Oklahoma has undertaken with IBM Watson, as a 2017 CIO 100 award winner, which recognizes 100 organizations for their business and technology innovation.

At the EDUCAUSE Annual Conference taking place this week in Philadelphia, the University of Oklahoma will discuss with IBM their path to deploying augmented intelligence and the value it provides to higher education.

Executive Vice President and Vice President for Administration and Finance, University of Oklahoma

More Data Analytics stories

Medicine and the Message: Consumer Engagement and the Power of Nontraditional Data

The journal Health Affairs estimates that the U.S. spends nearly $500 billion annually on pharmaceutical treatments. Focusing on clinical value alone isn’t enough to meet business growth targets — customer experience plays a critical role in long-term brand success. But experience doesn’t occur in isolation: To win trust and boost spending, pharma brands must use […]

Continue reading