A Hybrid SEM-PLS and ANN Approach for Predicting Student Loyalty in Higher Education Learning Management Systems
Journal of Information Systems and Informatics · 23.06.2026 · 8 (3) · 3333-3359
DOI: 10.63158/journalisi.v8i3.1625 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Information Systems and Informatics, online erschienen am 23.06.2026. Verfasst von Hamidah und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study aims to develop a hybrid Structural Equation Modeling–Partial Least Squares (SEM-PLS) and Artificial Neural Network (ANN) approach to analyze student loyalty in Learning Management Systems (LMS) at ISB Atma Luhur. Data were collected from 200 students at ISB Atma Luhur, representing a single-institution sample, and analyzed using SEM-PLS to examine causal relationships and ANN (Multilayer Perceptron) implemented in SPSS to support predictive analysis. The model includes e-service quality, user experience, information quality, and system quality as predictors of satisfaction and loyalty. The SEM-PLS results show that E-Service Quality (β = 0.350), System Quality (β = 0.170), and User Experience (β = 0.292) significantly affect Satisfaction, whereas Information Quality is not statistically significant (p = 0.054). Satisfaction positively influences Loyalty (β = 0.360), and User Experience has the strongest direct effect on Loyalty (β = 0.484). The model explains a substantial proportion of variance (R² = 0.717 and 0.631) with positive Q² values (0.460 and 0.379). Across ten independent runs, the ANN model achieved an average accuracy of 84.88% (SD = 2.82) and an average AUC of 0.949 (SD = 0.003), indicating stable predictive performance, indicating promising predictive performance under the current testing configuration. The findings provide context-specific explanatory and predictive insights into student loyalty in LMS, however, they should be interpreted with caution due to discriminant-validity limitations and the single-institution setting of the study.
Zitieren
APA
Hamidah, Sarwindah, Hengki, & Sugihartono, T. (2026). A Hybrid SEM-PLS and ANN Approach for Predicting Student Loyalty in Higher Education Learning Management Systems. Journal of Information Systems and Informatics, 8(3), 3333-3359. https://doi.org/10.63158/journalisi.v8i3.1625
Vancouver
Hamidah, Sarwindah, Hengki, Sugihartono T. A Hybrid SEM-PLS and ANN Approach for Predicting Student Loyalty in Higher Education Learning Management Systems. Journal of Information Systems and Informatics. 2026;8(3):3333-3359. doi:10.63158/journalisi.v8i3.1625
BibTeX
@article{Hamidah2026,
author = {Hamidah and Sarwindah and Hengki and Sugihartono, Tri},
title = {A Hybrid SEM-PLS and ANN Approach for Predicting Student Loyalty in Higher Education Learning Management Systems},
journal = {Journal of Information Systems and Informatics},
year = {2026},
volume = {8},
number = {3},
pages = {3333--3359},
doi = {10.63158/journalisi.v8i3.1625}
}
EUVIMED