arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.06805stat.APcs.LG
收藏

基于树型聚类技术的南非高等教育投入预测

Predicting Higher Education Throughput in South Africa Using a Tree-Based Ensemble Technique

University of Witwatersrand(威特沃特斯兰德大学);University of Johannesburg(约翰内斯堡大学)

Rendani Mbuvha, Patience Zondo, Aluwani Mauda, Tshilidzi Marwala

摘要:

我们使用梯度推进机和逻辑斯谛回归来预测在南非大学的学术吞吐量。结果突出了社会经济因素和研究领域作为吞吐量的预测因素的显着影响。我们进一步发现,社会经济因素成为一个相对于研究领域的预测随着时间的增加完成。我们提供干预措施,以抵消已确定的影响,其中包括学术,心理和财政支持的建议。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑