Predicting Student Loyalty in Higher Education Using Machine Learning - A Random Forest Approach

Aug 5, 2026

Student loyalty is a key determinant of higher education sustainability, influencing retention, institutional reputation, student engagement, and long-term financial stability. This study predicts student loyalty through a machine learning framework using the random forest algorithm. Data were collected via questionnaires from 107 students in Palembang and included service quality, emotional attachment, brand satisfaction, brand trust, and socio-economic conditions. After preprocessing, model training, and evaluation, performance was measured with accuracy, precision, recall, and F1-score. Results show an accuracy of 90.9%, supporting evidence-based strategies to strengthen loyalty.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Importance of Student Loyalty

Related Work and Limitations of SEM

Role of Machine Learning in Education

Method and Model (Random Forest)

Data Collection and Variables

Preprocessing, Training, Evaluation

Results and Implications

Journal of Information Systems and Informatics Vol. 7, No. 1, March 2025 e-ISSN: 2656-4882 p-ISSN: 2656-5935 DOI: 10.51519/journalisi.v7i1.977 Published By DRPM-UBD Predicting Student Loyalty in Higher Education Using Machine Learning: A Random Forest Approach Qoriani Widayati1, Kusworo Adi2, R Rizal Isnanto3, Eka Puji Agustini4, Dewa Rizki Rahmat Julianto5, Fawwaz Bimo Prakasa6 1,2,3, Doctoral Program of Information Systems, School of Postgraduate Studies, Diponegoro University, Semarang, Indonesia 1Accounting Information System, Bina Darma University, Palembang, Indonesia 4,5,6Information System Department, Bina Darma University, Palembang, Indonesia [Email:](Email:1 qoriani_widayati@binadarma.ac.id2 eka_puji@binadarma.ac.id)[1](Email:1 qoriani_widayati@binadarma.ac.id2 eka_puji@binadarma.ac.id)[ qoriani_widayati@binadarma.ac.id](Email:1 qoriani_widayati@binadarma.ac.id2 eka_puji@binadarma.ac.id)[2](Email:1 qoriani_widayati@binadarma.ac.id2 eka_puji@binadarma.ac.id)[ eka_puji@binadarma.ac.id](Email:1 qoriani_widayati@binadarma.ac.id2 eka_puji@binadarma.ac.id) Abstract Student loyalty is a crucial factor supporting the sustainability of higher education institutions. The aim of this study is to predict student loyalty using a machine learning approach, specifically the random forest algorithm. The data for this research were collected through a questionnaire that included variables such as service quality, emotional attachment, brand satisfaction, brand trust, and socio-economic conditions, distributed to 107 students in Palembang. The resulting dataset was processed through preprocessing, model training, and performance evaluation, employing metrics such as accuracy, precision, recall, and F1-score. The analysis using the random forest algorithm achieved an accuracy of 90.9% . These findings are expected to provide valuable insights for higher education institutions in developing more effective strategies to enhance student loyalty. Keywords: student loyalty, random forest, machine learning 1. INTRODUCTION Student loyalty to higher education institutions is crucial for the success and growth of these institutions. Building positive relationships with students and providing satisfying learning experience are long-term investments that higher education institutions can make. These efforts not only contribute to the long-term success of the institution but also foster increased student loyalty [1] . There are several reasons why student loyalty is crucial for higher education institutions. Firstly, it plays a key role in student retention, enhances the institution's image and reputation—particularly regarding institutional accreditation, encourages student participation and engagement in campus activities, and has a positive impact on the teaching system. Moreover, loyal students contribute to the institution’s financial stability and strengthen alumni relations, as they remain connected to the institution and continue to contribute even after graduation [2] . 63 This work is licensed under a Creative Commons Attribution 4.0 International License. p-ISSN: 2656-5935 [http://journal-isi.org/index.php/isi](http://journal-isi.org/index.php/isi) e-ISSN: 2656-4882 In the context of higher education, a loyal student is one who remains enrolled atthe institution and does not transfer to another university until completing their studies. Additionally, loyal students are more likely to pursue further education atthe same institution and to provide positive word-of-mouth recommendations, sharing their experiences with family, friends, and acquaintances whenever the opportunity arises. Therefore, it is essential for policymakers and administrators in higher education institutions to identify the factors that contribute to student loyalty [3] . Higher education institutions encounter several challenges in enhancing student loyalty, such as limitations in managing student and alumni data—both in terms of hum

FAQs

What is the main objective of this study?

The study aims to predict student loyalty in higher education using a machine learning approach, specifically the random forest algorithm.

What data and variables were used to build the model?

Questionnaire data from 107 students were used, covering service quality, emotional attachment, brand satisfaction, brand trust, and socio-economic conditions.

How was model performance evaluated and what was the result?

The model was evaluated using accuracy, precision, recall, and F1-score, achieving an accuracy of 90.9%.

Aug 5, 2026

Upload by River Wang