Using Latent Variable Models to Observe Academic Pathways
This provides a quantitative framework for university administrators and educational researchers to understand student choices, though it is incremental as it builds on existing probabilistic and multilabel classification methods.
The authors tackled the problem of modeling student course enrollment patterns by proposing a Gaussian latent variable model that learns the joint distribution over enrollments from ten years of anonymized transcripts, demonstrating its efficacy compared to other methods like deep learning architectures.
Understanding large-scale patterns in student course enrollment is a problem of great interest to university administrators and educational researchers. Yet important decisions are often made without a good quantitative framework of the process underlying student choices. We propose a probabilistic approach to modelling course enrollment decisions, drawing inspiration from multilabel classification and mixture models. We use ten years of anonymized student transcripts from a large university to construct a Gaussian latent variable model that learns the joint distribution over course enrollments. The models allow for a diverse set of inference queries and robustness to data sparsity. We demonstrate the efficacy of this approach in comparison to others, including deep learning architectures, and demonstrate its ability to infer the underlying student interests that guide enrollment decisions.