Using student performance predictions in a computer science curriculum

Abstract

Professors often develop anecdotal guidelines about how each student's past performance in their academic major relates to their performance in later courses. While these guidelines can be useful, a more formal statistical analysis of these relationships can provide valuable insight into predicted student performance, which can help professors guide their students to focus on potential areas of difficulty. In addition, such analyses can identify which courses are key indicators of later performance in the major. This additional insight into the relationships between the courses in the curriculum can help professors implement curriculum changes and measure the effects of those changes. In this paper, we present the results of such an analysis for computer science majors at the U.S. Air Force Academy.