Predicting Higher Education Throughput in South Africa Using a Tree-Based Ensemble Technique
Applications
2021-06-15 v1 Machine Learning
Abstract
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.
Cite
@article{arxiv.2106.06805,
title = {Predicting Higher Education Throughput in South Africa Using a Tree-Based Ensemble Technique},
author = {Rendani Mbuvha and Patience Zondo and Aluwani Mauda and Tshilidzi Marwala},
journal= {arXiv preprint arXiv:2106.06805},
year = {2021}
}