Title: Predicting higher education student performance with educational data mining technique

Authors: William William; Tya Wildana Hapsari Lubis; Suci Pertiwi

Addresses: Undergraduate Program of Management, School of Business, Universitas Mikroskil, Medan, Indonesia ' Undergraduate Program of Management, School of Business, Universitas Mikroskil, Medan, Indonesia ' Undergraduate Program of Management, School of Business, Universitas Mikroskil, Medan, Indonesia

Abstract: Predicting student performance in higher education is critical for enhancing the academic outcomes of students. This study conducted on undergraduate students at STMIK Mikroskil and STIE Mikroskil in Medan, Indonesia, deals with a research gap by exploring factors beyond conventional metrics like cumulative grade point average (CGPA). The unique Indonesian educational landscape introduces additional factors, including graduation time and lecturer competency. Acknowledging the importance of student behaviour and lecturer competency, the study employs an artificial neural network model to predict student performance. By considering variables such as entry pathway, attendance, grade point average (GPA), scholarship, and lecturer performance index, the model achieves high accuracy - 85.33% for CGPA and 77.43% for graduation time. This research contributes to adopting educational data mining, aligning with Indonesian education regulations and facilitating early identification of at-risk students for targeted interventions.

Keywords: performance prediction; cumulative grade point average; CGPA; graduation time; artificial neural network; ANN; grade point average; GPA.

DOI: 10.1504/IJSSS.2024.140457

International Journal of Society Systems Science, 2024 Vol.15 No.1, pp.23 - 43

Received: 23 May 2023
Accepted: 25 Dec 2023
Published online: 19 Aug 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article