Using Learning Analytics and Visualization Techniques to Evaluate the Structure of Higher Education Curricula

Abstract

In this paper, we propose a data mining technique that evaluates a curriculum's structure based on academic data collected from Computer Science students from 2005 to 2016. Our approach is based on the Synthetic Control Method (SCM), which builds a linear model describing the relation between courses based on student performance information. The proposed model is compared to a linear regression model with positive coefficients. In addition to providing the relation between courses, it can also be used to predict students’ grades in a specific course based on their previous grades. The results are visualized in a user-friendly tool, which allows for contrast and comparison between the official structure and the structure found based on the data.