Predicting Math Student Success in the Initial Phase of College With Sparse Information Using Approaches From Statistical Learning

Abstract

In math teacher education, dropout research relies mostly on frameworks which carry out extensive variable collections leading to a lack of practical applicability. We investigate the completion of a first semester course as a dropout indicator and thereby provide not only good predictions, but also generate interpretable and practicable results together with easy-to-understand recommendations. As proof-of-concept, a sparse feature space together with machine learning methods is used for prediction of dropout, wherein the most predictive features have to be identified. Interpretability can be reached by introducing risk groups for the students. Implications for interventions are discussed.