Title: Predicting student success in an online Master of Business Administration program

Authors: Morgan McCarthy; William A. Young II; Hoda Rahmani; Ashley Y. Metcalf

Addresses: Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA 15213, USA ' Ohio University, Athens OH 45701, USA ' Ohio University, Athens OH 45701, USA ' Ohio University, Athens OH 45701, USA

Abstract: Online Master of Business Administration programs have been growing in popularity as an alternative to traditional Master of Business Administration Programs. The literature on academic success has highlighted the use of academic analytics to predict student performance. The purpose of this study is to determine the most significant indicators of student success using student admissions data of an online Master of Business Administration program. Four types of models are constructed in this research including logistic regression, discriminant analysis, classification trees, and neural networks. The best model is selected using classification goodness of fit metrics. The results of this study indicate that applicants' admissions decision and students' academic standing are best predicted using a reduced logistic regression and discriminant analysis models, respectively.

Keywords: machine learning; academic performance; online Master of Business Administration; logistic regression; discriminant analysis; decision trees; neural networks; academic analytics; student success.

DOI: 10.1504/IJSSS.2023.132695

International Journal of Society Systems Science, 2023 Vol.14 No.3, pp.201 - 221

Received: 13 Nov 2021
Received in revised form: 04 Nov 2022
Accepted: 22 Nov 2022
Published online: 08 Aug 2023 *