Improving Academic Pathways by Mining University Data

• In Event: Learning Analytics in Higher Education: Exploring Big Data on Campus

Abstract

An enduring issue in higher education is student retention to successful graduation. National studies report that average six-year graduation rates across higher-education institutions is 59% and have remained relatively stable over the last 15~years. In my talk I will present new computational methods designed to analyze in a comprehensive manner, the large and diverse types of education and learning-related data in order to improve undergraduate education. Particularly, these methods model and identify the dynamics of student knowledge and use them to determine the student's state of knowledge and predict the student's grades in future courses. I will provide a case study on analyzed data from course management system (CMS) at University of Minnesota. These student-targeted applications can assist students in planning their academic pathways, help provide advisors detailed information about the student's current state of knowledge and learning preferences, identifies at risk students, and provides alternative degree programs that fit to the student's unique characteristics.

Author

• George Karypis, University of Minnesota