Personalizing the Education Experience

Using Data to Personalize Education

Completing a postsecondary education has become critically important to the likelihood of well-being and thriving after graduation. As students acquire additional educational credentials, they not only become more likely to be employed and to earn a better wage, but they are also more likely to be civically-engaged and healthier.

Despite this, there is a growing gap between need for employment that requires postsecondary training (about 65% of jobs) and the percentage of working-age Americans with such credentials (about 40%). Consequently, colleges and universities are under pressure to increase retention and completion rates to keep up with the demand for quality education and training.

At the same time, the profile of the typical college students has changed significantly over the past several decades. More than ever, students are more likely to be over the age of 25, first-gen students, students of color, working full-or part-time, part-time students, and parents. As such, these students demand for a more personalized learning experience—one that is tailored to their individual needs and goals.

As access to student data becomes more abundantly available from various sources (e.g., including administrative, academic, demographic, and social), educational institutions are recognizing the potential to create a more complete understanding of their students’ needs and trajectories.

Educational institutions are now using data and data-analytics to provide more customized and meaningful learning experiences for their students. When applied effectively, data-driven education has the potential to encourage student success and retention, facilitate more effective instruction, advising and administration, and reduce inequalities in access and achievement.

As schools continue to invest in better management, interpretation, and utilization of student data, some early adopters of these data-informed strategies are showing some beneficial effects on student retention and persistence rates. Below are the most common applications of student-data with goal of creating more personalized learning experiences:

1. Using data to inform the pace, content, and structure of in-class learning. Such strategies include competency-based progression of academic trajectories; adaptive learning technology to tailor course content and pace to the individual learner; and non-traditional instruction strategies (e.g., blended learning, online, or flipped classroom structures).

2. Analyzing historical data to create risk profiles for students, with the hope of being able to identify students with the greatest potential need, and consequently connecting them with the resources they need to minimize disruptions

3. Using historical and real-time data-analytics to improve advising—often called Integrated Planning and Advising for Student Success (iPASS). These can include the development of advanced student case management platforms that are both advisor- and student-facing.

4. Early alert systems to inform advisors, faculty, and students about early signs of difficulty. For instance, if a student misses a certain number of classes; if they fail key gatekeeper courses for an intended major; or simply reminder tools to update students about upcoming milestones or opportunities.

While the evidence for the effectiveness of such strategies continues to grow, we are also learning about obstacles that can potentially limit the reliable scalability of any given strategy. For example, school leaders are struggling to strike a balance between safeguarding sensitive student data and being able to collect and use such data to individualize learning. Postsecondary institutions are also facing challenges in making their personalized learning strategies work, and in determining how to evaluate the true impact of those strategies on student learning. Finally, the human expertise to manage, analyze, and interpret the data can add to the (often) significant costs of effective implementation.