Comparative Analysis of Classification Performance for U.S. College Enrollment Predictive Modeling Using Four Machine Learning Algorithms (Logistic Regression, Decision Tree, Support Vector Machine, Artificial Neural Network)

Autor/in	Kye, Anna
Titel	Comparative Analysis of Classification Performance for U.S. College Enrollment Predictive Modeling Using Four Machine Learning Algorithms (Logistic Regression, Decision Tree, Support Vector Machine, Artificial Neural Network)
Quelle	(2023), (206 Seiten) PDF als Volltext Verfügbarkeit Ph.D. Dissertation, Loyola University Chicago
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
ISBN	979-8-3797-2388-0
Schlagwörter	Hochschulschrift; Dissertation; Comparative Analysis; Classification; College Enrollment; Prediction; Artificial Intelligence; Algorithms; Regression (Statistics); Models; Enrollment Management + Suchen Sie Ihr Suchwort? Thesis; Dissertations; Academic thesis; Classification system; Klassifikation; Klassifikationssystem; Vorhersage; Künstliche Intelligenz; Algorithm; Algorithmus; Regression; Regressionsanalyse; Analogiemodell
Abstract	Every year, the national high school graduation rate is declining and impacting the number of students applying to colleges. Moreover, the majority of students are applying to more than one college. This makes a lot of colleges to be highly competitive in student recruitment for enrollment and thus, the necessity for institutions to anticipate uncertainties related to budgets expected from student enrollment has increased. Hence enrollment management has become a pivotal sector in higher education institutions. Data and analytics are now a crucial part of enhancing enrollment management. Through big data analytics-driven solutions, institutions expect to improve enrollment by identifying students who are most likely to enroll in college. Machine learning can unlock significant value for colleges by allocating resources effectively to improve enrollment and budgeting. Therefore, a machine learning method is a vital tool for analyzing a large amount of data, and predictive analytics using this method has become a high demand in higher education. Yet higher education is still in the early stages of utilizing machine learning for enrollment management. In this study, I applied four machine learning algorithms to seven years of data on 108,798 students, each with 50 associated features, admitted to a 4-year, non-profit university in Midwest urban area to predict students' college enrollment decisions. By treating the question of whether students offered admission will accept it as a binary classification problem, I implemented four machine learning algorithm classifiers and then evaluate the performance of these algorithms using the metrics of accuracy, sensitivity, specificity, precision, F-score, and area under the ROC and PR curves. The results from this study will indicate the best-performed prediction modeling of students' college enrollment decisions. This research will expand the case and knowledge of utilizing machine learning methods in the higher education sector, focused on the U.S. College enrollment management field. Moreover, it will expand the knowledge of how the machine learning prediction model can be pragmatically used to support institutions in setting up student enrollment management strategies. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.] (As Provided).
Anmerkungen	ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com/en-US/products/dissertations/individuals.shtml
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01