Predicting college GPA using machine learning: an analysis of key academic performance factors
International Journal of Engineering Approaches · 17.06.2026 · 3 (1) · 73-93
DOI: 10.66160/ijea.1914980 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Engineering Approaches, online erschienen am 17.06.2026. Verfasst von Elif Beyza Akyar und 2 weiteren Autor:innen. Die Arbeit nennt 113 Literaturangaben.
Abstract (Originalsprache)
The NetHealth project, uses data collected from University of Notre Dame students through surveys and health measurements between 2015 and 2019.722 students were enrolled in two-year-long study, and another 300 students for an additional two years. The aim of the study is to identify influential factors on the student’s Grade Point Average (GPA) by using the NetHealth project survey outputs. After the data-cleaning process, a set of 265 students took place in the study. Machine learning is applied to visualize and interpret the outputs such as decision trees, support vector machines, logistic regression, cross-validation, and stratified cross-validation. Potential factors are selected to analyze their effect on GPA by categorizing in multiple subsets. GPA is defined as categorical variable used as a measure of academic success. As a result, the highest accuracy is achieved using the decision tree algorithm with subset 2 by accuracy of 74.50%. However, to support the findings, cross validation method is implemented. The unexpected result of decreased accuracy in cross validation implication on subset 2, it brings about the necessity of focusing on the second highest accuracy level which is addressed in subset 1 with 72.52%. As a conclusion, the subset 1 is performed best among two high resulted methods with the factors, use of internet, email, other leisure, used tobacco, high school type, parent income, happy, special type of diet, likes to cooperate with others, and tends to be lazy.
Zitieren
APA
Akyar, E. B., Kabaoğlu, C., & Ulku, I. (2026). Predicting college GPA using machine learning: an analysis of key academic performance factors. International Journal of Engineering Approaches, 3(1), 73-93. https://doi.org/10.66160/ijea.1914980
Vancouver
Akyar EB, Kabaoğlu C, Ulku I. Predicting college GPA using machine learning: an analysis of key academic performance factors. International Journal of Engineering Approaches. 2026;3(1):73-93. doi:10.66160/ijea.1914980
BibTeX
@article{Akyar2026,
author = {Akyar, Elif Beyza and Kabaoğlu, Ceren and Ulku, Ilayda},
title = {Predicting college GPA using machine learning: an analysis of key academic performance factors},
journal = {International Journal of Engineering Approaches},
year = {2026},
volume = {3},
number = {1},
pages = {73--93},
doi = {10.66160/ijea.1914980}
}
EUVIMED