A Comparative Analysis of Regression and Neural Networks for University Admissions
Document Type
Article
Publication Date
10-1-1999
Keywords
neural networks, categorization, admissions, enrollment ratio, logistic regression, backpropagation
Digital Object Identifier (DOI)
https://doi.org/10.1016/S0020-0255(99)00057-2
Abstract
Universities are faced annually with a tremendous quantity of student applicants. The size of the applicant pool taxes the resources of the admissions staff. If admissions counselors are able to spend a greater amount of time with individual applicants, then the enrollment yield (total number of enrollments) from these applicants will increase. Neural networks provide a method for categorizing student applicants and determining the likelihood that they will enroll at an institution if accepted. A comparison of neural networks against the traditional modeling technique of logistic regression is performed to show improvements gained via neural networks. The developed neural networks effectively halved the student applicant load for each counselor at a small private university.
Was this content written or created while at USF?
Yes
Citation / Publisher Attribution
Information Sciences, v. 119, issues 1-2, p. 1-20
Scholar Commons Citation
Walczak, Steven and Sincich, Terry, "A Comparative Analysis of Regression and Neural Networks for University Admissions" (1999). School of Information Faculty Publications. 209.
https://digitalcommons.usf.edu/si_facpub/209
