Predicting Higher Education Throughput in South Africa Using a Tree-Based Ensemble Technique
This addresses student success and resource allocation in higher education in South Africa, but is incremental as it applies existing methods to a specific context.
The study tackled predicting academic throughput at a South African university using gradient boosting machines and logistic regression, finding that socio-economic factors and field of study are significant predictors, with socio-economic influence decreasing relative to field of study over time.
We use gradient boosting machines and logistic regression to predict academic throughput at a South African university. The results highlight the significant influence of socio-economic factors and field of study as predictors of throughput. We further find that socio-economic factors become less of a predictor relative to the field of study as the time to completion increases. We provide recommendations on interventions to counteract the identified effects, which include academic, psychosocial and financial support.