Vol.65, No.2, 2020, pp.1825-1836, doi:10.32604/cmc.2020.010011
OPEN ACCESS
ARTICLE
Who Will Come: Predicting Freshman Registration Based on Decision Tree
  • Lei Yang1, Li Feng1, *, Liwei Tian1, Hongning Dai1
1 Macau University of Science and Technology, Macau.
* Corresponding Author: Li Feng. Email: .
Received 04 February 2020; Accepted 30 May 2020; Issue published 20 August 2020
Abstract
The registration rate of freshmen has been a great concern at many colleges and universities, particularly private institutions. Traditionally, there are two inquiry methods: telephone and tuition-payment-status. Unfortunately, the former is not only time-consuming but also suffers from the fact that many students tend to keep their choices secret. On the other hand, the latter is not always feasible because only few students are willing to pay their university tuition fees in advance. It is often believed that it is impossible to predict incoming freshmen’s choice of university due to the large amount of subjectivity. However, if we look at the two major considerations a potential freshman contemplates in making a choice, such as the geographical location of the university in relation to his/her home town, and testimonies about of that college life experience by previous graduates, we believe it is possible to predict future enrollment decisions. This paper is the first to find a way to solve the problem of predicting the choice of university a freshman will attend. Our contributions include the following: 1. we present a dataset on freshman registration; 2. we propose a decision-tree-based approach for freshman registration prediction. Study results show that freshman registration is predictable.
Keywords
Decision tree, prediction, registration.
Cite This Article
L. Yang, L. Feng, L. Tian and H. Dai, "Who will come: predicting freshman registration based on decision tree," Computers, Materials & Continua, vol. 65, no.2, pp. 1825–1836, 2020.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.