Work in Progress: Utilizing Decision Tree Analysis for Engineering Students' GPA Prediction

Document Type

Conference Proceeding

Publication Date

1-1-2024

Abstract

Students' grade point average (GPA) is an important indicator of students' academic success. In our work-in-progress study, we utilized decision tree analysis to investigate patterns in predicting the GPA of engineering students, considering various demographic, socioeconomic, and academic aspects. Our analysis of the dataset consisting of engineering students' academic records revealed several key insights. First, SAT scores emerged as a central factor in GPA prediction, with higher scores predicting better GPAs. Second, socioeconomic status also became evident among students with high SAT scores, reflecting the impact of background characteristics on academic achievements. Lastly, parent education level also stood out as significant, showing that students with highly educated parents generally achieved higher GPAs, underlining family educational background's role in success. Overall, our research adds to the existing literature by illuminating the intricate factors influencing engineering students' GPA and provides an example of utilizing decision tree-based quantitative methods in engineering education research.

Identifier

85192014959 (Scopus)

ISBN

[9798350348729]

Publication Title

EDUNINE 2024 - 8th IEEE World Engineering Education Conference: Empowering Engineering Education: Breaking Barriers through Research and Innovation, Proceedings

External Full Text Location

https://doi.org/10.1109/EDUNINE60625.2024.10500587

This document is currently not available here.

Share

COinS