dc.rights.license | CC-BY-NC-ND | |
dc.contributor.advisor | Barkema, G.T. | |
dc.contributor.author | Hsu, Sarah | |
dc.date.accessioned | 2022-07-22T00:01:17Z | |
dc.date.available | 2022-07-22T00:01:17Z | |
dc.date.issued | 2022 | |
dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/41849 | |
dc.description.abstract | The influx of students is not only an important source of academic deployment but also influences national development. Higher education in the Netherlands has expanded rapidly in the last two decades, and the Dutch labour market also needs these talented people in the fastest-growing ICT industry. It is essential for the university to forecast the incoming students and avoid adverse effects in response to the rising student population. In this thesis, the XGBoost Regression algorithm is proposed to predict the Master's student influx in the following five years and investigate the feature importance of the student population. The model is trained by the background information of Bachelor’s students to estimate the long-term growth of the Master’s student influx in Computing Science. The findings and analysis can provide objective references to initiate the educational strategy. | |
dc.description.sponsorship | Utrecht University | |
dc.language.iso | EN | |
dc.subject | This research aims to predict the number of students enrolled in the Master's programme of Computing Science at Utrecht University in the coming five years as well as find the dominant features which have a significant influence on the student influx. | |
dc.title | Long-term Prediction of Master Student Influx in Computing Science | |
dc.type.content | Master Thesis | |
dc.rights.accessrights | Open Access | |
dc.subject.keywords | Machine Learning; XGBoost Regression; Sliding Window; Education | |
dc.subject.courseuu | Applied Data Science | |
dc.thesis.id | 6222 | |