Next Article in Journal
Unified Genetic Algorithm Approach for Solving Flexible Job-Shop Scheduling Problem
Next Article in Special Issue
Online Blended Learning in Small Private Online Course
Previous Article in Journal
Bearing Severity Fault Evaluation Using Contour Maps—Case Study
Previous Article in Special Issue
Towards Predicting Student’s Dropout in University Courses Using Different Machine Learning Techniques
Article

Quantifying the Impact of Student Enrollment Patterns on Academic Success Using a Hidden Markov Model

Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL 32816, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Juan A. Gómez-Pulido
Appl. Sci. 2021, 11(14), 6453; https://doi.org/10.3390/app11146453
Received: 5 May 2021 / Revised: 8 June 2021 / Accepted: 8 June 2021 / Published: 13 July 2021
(This article belongs to the Special Issue Data Analytics and Machine Learning in Education)
Simplified classifications have often led to college students being labeled as full-time or part-time students. However, student enrollment patterns can be much more complicated at many universities, as it is common for students to switch between full-time and part-time enrollment each semester based on finances, scheduling, or family needs. While previous studies have identified part-time enrollment as a risk factor to students’ academic success, limited research has examined the impact of enrollment patterns or strategies on academic performance. Unlike traditional methods that use a single-period model to classify students into full-time and part-time categories, in this study, we apply an advanced multi-period dynamic approach using a Hidden Markov Model to distinguish and cluster students’ enrollment strategies into three categories: full-time, part-time, and mixed. We then investigate and compare the academic performance outcomes of each group based on their enrollment strategies while taking into account student type (i.e., first-time-in-college students and transfer students). Analysis of undergraduate student records data collected at the University of Central Florida from 2008 to 2017 shows that the academic performance of first-time-in-college students who apply a mixed enrollment strategy is closer to that of full-time students, as compared to part-time students. Moreover, during their part-time semesters, mixed-enrollment students significantly outperform part-time students. Similarly, analysis of transfer students shows that a mixed-enrollment strategy is correlated with similar graduation rates as the full-time enrollment strategy and more than double the graduation rate associated with part-time enrollment. This finding suggests that part-time students can achieve better overall outcomes by increased engagement through occasional full-time enrollments. View Full-Text
Keywords: student enrollment pattern; Hidden Markov model; academic outcomes; first-time-in-college students; transfer students student enrollment pattern; Hidden Markov model; academic outcomes; first-time-in-college students; transfer students
Show Figures

Figure 1

MDPI and ACS Style

Boumi, S.; Vela, A.E. Quantifying the Impact of Student Enrollment Patterns on Academic Success Using a Hidden Markov Model. Appl. Sci. 2021, 11, 6453. https://doi.org/10.3390/app11146453

AMA Style

Boumi S, Vela AE. Quantifying the Impact of Student Enrollment Patterns on Academic Success Using a Hidden Markov Model. Applied Sciences. 2021; 11(14):6453. https://doi.org/10.3390/app11146453

Chicago/Turabian Style

Boumi, Shahab, and Adan E. Vela 2021. "Quantifying the Impact of Student Enrollment Patterns on Academic Success Using a Hidden Markov Model" Applied Sciences 11, no. 14: 6453. https://doi.org/10.3390/app11146453

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop