Degree

Doctor of Philosophy (PhD)

Department

Stephenson Department of Entrepreneurship and Information Systems

Document Type

Dissertation

Abstract

In today’s world, students can face many challenges along the way to graduation, both from within and without the university. To facilitate greater student success, and thus improve university metrics, we seek a way to provide insight to both student and department when it comes to optimizing the course selection and sequencing process. To that end, we hypothesize a process that will provide recommendations to students based on similar students who were successful before them, and then utilize the aggregate of the recommendations to provide information to departments about course needs so that students will have courses available to them when they need it. This will be implemented by three types of techniques: clustering, collaborative filtering, and linear programming to identify an assignment of courses to semesters that will maximize a dual mandate of high grade point average (GPA) and probability of graduation based on how similar students performed in the past

Date

11-2021

Committee Chair

Schneider, Helmut

DOI

10.31390/gradschool_dissertations.5708

Available for download on Wednesday, November 15, 2028

Share

COinS