Course-Graph Discovery from Academic Performance Using Nonnegative LassoNet

This paper focuses on the problem of mining a course graph from students’ academic grades in formal education, which is an essential topic for artificial intelligence in education (AIED). However, most current methods often suffer from hardly understanding associations in practice. To this end, we formulate this problem into a feature selection schema that the proposed nonnegative LassoNet can solve. In the study case, we use the course scores of 4,577 records in the computer science department at our university. From the study results, our method achieves about 78% accuracy in score prediction with an acceptable error, which is better than traditional regression models with shrinkage. Based on the sparse self-expressive representation, we create a course map to show the associations behind the student’s academic performance, providing pieces of evidence for education studies and triggering exciting discoveries.