Predicting the Academic Performance of Industrial Engineering Students Based on Socioeconomic Background and Past Achievements: A Two-step Blending-based Ensemble Approach

DOI

10.2991/978-94-6463-554-6_52How to use a DOI?

Keywords

Academic Performance Prediction; University Students; Industrial Engineering; Machine Learning; Ensemble Learning

Abstract

The academic success of students is of utmost importance for higher education institutions. Therefore, accurately predicting students’ academic performance is essential, and early interventions are necessary to improve their achievements. This research focuses on predicting the academic performance of new students and proposes a two-step ensemble learning-based approach for this purpose. A two-step ensemble learning-based approach can improve generalization and predictive ability. It provides a general overview of evaluation actions that both the university and the students can take. Additionally, it aims to contribute to the literature on predicting the academic performance of new students. The results of the conducted research demonstrate that the proposed model outperforms the elastic net model with an accuracy of 87.8% and a kappa value of 81.8%. The high result of the proposed model can be categorized as having good performance. The study also analyzes the variables influencing each model used in this case study. Notably, the top ten variables serving as significant features were identified: first semester GPA, number of failed classes, number of absences, achievement in academic competitions, mother's monthly income, high school GPA, quality of family relationship, scholarship status, hometown location, and travel time to the university.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Alvin Muhammad ‘Ainul Yaqin
AU  - Priskila Destriani Banjarnahor
AU  - Vridayani Anggi Leksono
AU  - Bayu Nur Abdallah
AU  - Mifthahul Janna Rosyid
PY  - 2024
DA  - 2024/11/29
TI  - Predicting the Academic Performance of Industrial Engineering Students Based on Socioeconomic Background and Past Achievements: A Two-step Blending-based Ensemble Approach
BT  - Proceedings of the 4th International Conference on Education and Technology (ICETECH 2023)
PB  - Atlantis Press
SP  - 634
EP  - 645
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6463-554-6_52
DO  - 10.2991/978-94-6463-554-6_52
ID  - Yaqin2024
ER  -