What Can Be Learned By Grading Analytics?

This article looks at useful applications of Grading Analytics, i.e. the analysis of data in a conventional student information system of a university. Much research in educational data mining focuses on Learning Analytics, a field that heavily exploits data that comes from digital footprints of students as they use online learning tools and learning management systems. In contrast, our work uses primarily grades as raw features for the analysis of the learning and the teaching process. Based on the data of a typical student record in a German university, we present a comparison of different methods for student success predictions. Our results suggest that deep neural networks can extract more accurate information from aggregative features than conventional methods. Given the powerful tools of modern data analytics, we look at applications of Grading Analytics for the improvement of a university's operations, in particular for the core mission of a university: helping students to successfully master their field of study.