Early dropout predictors in social sciences and management degree students

Bibliographic Data

ID14689752
AuthorsJosé M Ortiz-Lozano (0000-0002-8317-4393, Quantitative Methods Department, Universidad Pontificia Comillas (ICAI/ICADE), Madrid, Spain), Pilar Aparicio-Chueca (0000-0002-4697-5124, Universitat de Barcelona, corresponding author), Xavier M Triadó-Ivern (0000-0002-4938-6878, Universitat de Barcelona), Jose Luis Arroyo-Barrigüete (0000-0002-3660-3933, Quantitative Methods Department, Universidad Pontificia Comillas (ICAI/ICADE), Madrid, Spain)
Year2024
Volume49
Issue8
Pages1303-1316
Publication date2024-08-02
Peer ReviewedYes
Open AccessNo
TypeARTICLE
VenueStudies in Higher Education (JOURNAL)
Journal identifiersISSN: 0307-5079 • E-ISSN: 1470-174X
PublisherInforma UK Limited (PUBLISHER • GB)
DOI10.1080/03075079.2023.2264343
OpenAlexW4387186647
LanguageEN
Citations received5
References cited58

Student dropout is a major concern in studies investigating retention strategies in higher education. This study identifies which variables are important to predict student dropout, using academic data from 3583 first-year students on the Business Administration (BA) degree at the University of Barcelona (Spain). The results indicate that two variables, the percentage of subjects failed and not attended in the first semester, demonstrate significant predictive power. This has been corroborated with an additional sample of 10,784 students from three-degree programs (Law, BA, and Economics) at the Complutense University of Madrid (Spain), to assess the robustness of the results. Three different algorithms have also been utilized: neural networks, random forest, and logit. In the specific case of neural networks, the NeuralSens methodology has been employed, which is based on the use of sensitivities, allowing for its interpretation. The outcomes are highly consistent in all cases: both a simple model (logit) and more sophisticated ones (neural networks and random forest) exhibit high accuracy (correctly predicted values) and sensitivity (correctly predicted dropouts). In test set average values of 77% and 69% have been respectively achieved. In this regard, a noteworthy point is that only academic data from the university itself was used to develop the models. This ensures that there’s no dependence on other personal or organizational variables, which can often be difficult to access

Artificial neural network · Econometrics · Economics · Higher education · Logistic regression · Logit · Machine learning · Mathematics education · Predictive power · Statistics · Computer Science · Educational Outcomes and Influences · Higher Education Research Studies · Mathematics · Online Learning and Analytics · Psychology · Artificial Intelligence

Tools

Open DOI