Understanding Computer Science Academic Performance Using Principal Components Analysis

ASU Author/Contributor (non-ASU co-authors, if there are any, appear on document)
Christopher Smith (Creator)
Institution
Appalachian State University (ASU )
Web Site: https://library.appstate.edu/
Advisor
R. Mitchell Parry

Abstract: Some students perform better in school than others. Some classes are also harder than others. This thesis poses the question: Are there types of students that do better in certain types of classes? We model student grades as a combination of class difficulty, student GPA, and student-class preference using student transcript data for Computer Science undergraduates at Appalachian State University. This thesis applies principal components analysis to relate classes to each other, interprets these relationships, and quantifies their importance for grade estimation.

Additional Information

Publication
Thesis
Smith, C. (2017). Understanding Computer Science Academic Performance Using Principal Components Analysis. Unpublished Master’s Thesis. Appalachian State University, Boone, NC.
Language: English
Date: 2017
Keywords
Machine Learning, Principal Components Analysis

Email this document to