ANALYSIS OF FACTORS DETERMINING STUDENT SATISFACTION USING DECISION TREE, RANDOM FOREST, SVM, AND NEURAL NETWORKS: A COMPARATIVE STUDY

Andi Dwi Riyanto; Arif Mu'amar Wahid; Aniec Anafisah Pratiwi

doi:10.52436/1.jutif.2024.5.4.2188

Andi Dwi Riyanto Information System, Computer Science Faculty, Universitas Amikom Purwokerto, Indonesia
Arif Mu'amar Wahid Magister of Computer Science, Computer Science Faculty, Universitas Amikom Purwokerto, Indonesia
Aniec Anafisah Pratiwi Information System, Computer Science Faculty, Universitas Amikom Purwokerto, Indonesia

DOI: https://doi.org/10.52436/1.jutif.2024.5.4.2188

Keywords: decision tree, machine learning, neural networks, random forest, student satisfaction, SVM

Abstract

Student satisfaction is crucial in higher education, impacting student loyalty, retention rates, and institutional reputation. This study addresses the gap in applying advanced machine learning techniques to predict and understand key determinants of student satisfaction. The primary objective is to analyze and predict the factors determining student satisfaction using four machine learning models: Decision Tree, Random Forest, SVM, and Neural Networks. The dataset comprises 2527 entries with seven relevant features. Data preprocessing involved normalization and exploratory data analysis (EDA) to ensure accurate analysis. The Neural Network model achieved the highest accuracy with an MSE of 0.001399, RMSE of 0.037397, MAE of 0.030773, and R² of 0.998154, followed closely by the SVM model. These results suggest that advanced machine learning models, particularly Neural Networks and SVM, are effective in predicting student satisfaction and identifying key areas for improvement. This study contributes to understanding the determinants of student satisfaction using machine learning models, providing practical implications for educational administrators to develop targeted strategies to enhance student satisfaction by focusing on critical factors such as academic support and financial aid. The findings highlight the importance of using advanced predictive techniques to gain deeper insights into student satisfaction, thereby enabling institutions to implement more effective interventions. Future research should explore additional variables and more sophisticated model architectures to further improve predictive accuracy and expand the applicability of these models in educational settings.

Downloads

Download data is not yet available.

References

M. Bakrie, B. Sujanto, and R. Rugaiyah, “The Influence of Service Quality, Institutional Reputation, Students’ Satisfaction on Students’ Loyalty in Higher Education Institution,” Int. J. Educ. Vocat. Stud., vol. 1, no. 5, 2019, doi: 10.29103/ijevs.v1i5.1615.

D. Meštrović, “Service Quality, Students’ Satisfaction and Behavioural Intentions in STEM and IC Higher Education Institutions,” Interdiscip. Descr. Complex Syst., vol. 15, no. 1, pp. 66–77, 2017, doi: 10.7906/indecs.15.1.5.

F. M. Roget, P. F. Esparís, and E. V. Rozas, “University Student Satisfaction and Skill Acquisition: Evidence From the Undergraduate Dissertation,” Educ. Sci., vol. 10, no. 2, p. 29, 2020, doi: 10.3390/educsci10020029.

Tg Nur-Wina Tuan Abu Bakar, “Lecturer Competence and Student Satisfaction: A Roadmap for Quality Education,” Int. J. Acad. Res. Progress. Educ. Dev., vol. 12, no. 4, 2023, doi: 10.6007/ijarped/v12-i4/18970.

K. Fuchs and K. Fangpong, “Using the SERVQUAL Framework to Examine the Service Quality in Higher Education in Thailand,” Educ. Q. Rev., vol. 4, no. 2, 2021, doi: 10.31014/aior.1993.04.02.286.

M. K. G. Illanes, J. A. Gallegos-Mardones, and A. Z. Vasquez-Parraga, “Explaining Loyalty in Higher Education: A Model and Comparative Analysis From the Policy of Gratuity, a Case Applied to Chile,” Sustainability, vol. 13, no. 19, p. 10781, 2021, doi: 10.3390/su131910781.

S. Annamdevula, “Relationship Between Service Quality, Satisfaction, Motivation and Loyalty,” Qual. Assur. Educ., vol. 25, no. 2, pp. 171–188, 2017, doi: 10.1108/qae-04-2013-0016.

T. Djudin, “The Effect of Teaching Method and Lecture Program on Students’ Satisfaction Rates and Academic Achievement,” Jetl J. Educ. Teach. Learn., 2018, doi: 10.26737/jetl.v3i1.322.

L. Masserini, M. Bini, and M. Pratesi, “Do Quality of Services and Institutional Image Impact Students’ Satisfaction and Loyalty in Higher Education?,” Soc. Indic. Res., vol. 146, no. 1–2, pp. 91–115, 2018, doi: 10.1007/s11205-018-1927-y.

Z. Mihanović, A. B. Batinić, and J. Pavičić, “The Link Between Students’ Satisfaction With Faculty, Overall Students’ Satisfaction With Student Life and Student Performances,” Rev. Innov. Compet., vol. 2, no. 1, pp. 37–60, 2016, doi: 10.32728/ric.2016.21/3.

M. Topaloglu and G. Malkoç, “Decision Tree Application for Renal Calculi Diagnosis,” Int. J. Appl. Math. Electron. Comput., pp. 404–404, 2016, doi: 10.18100/ijamec.281134.

N. R. Mazahua, L. Rodríguez-Mazahua, A. López-Chau, and G. Alor-Hernández, “Comparative Analysis of Decision Tree Algorithms for Data Warehouse Fragmentation*,” Rev. Perspect. Empres., vol. 7, no. 2–1, pp. 31–43, 2020, doi: 10.16967/23898186.667.

C. Zhang, C. Liu, X. Zhang, and G. Almpanidis, “An Up-to-Date Comparison of State-of-the-Art Classification Algorithms,” Expert Syst. Appl., vol. 82, pp. 128–150, 2017, doi: 10.1016/j.eswa.2017.04.003.

T. Wakiya et al., “Prediction of Massive Bleeding in Pancreatic Surgery Based on Preoperative Patient Characteristics Using a Decision Tree,” Plos One, vol. 16, no. 11, p. e0259682, 2021, doi: 10.1371/journal.pone.0259682.

R. Shan, X. Xiao, J. Che, J. Du, and Y. Li, “Data Mining Optimization Software and Its Application in Financial Audit Data Analysis,” Mob. Inf. Syst., vol. 2022, pp. 1–7, 2022, doi: 10.1155/2022/6851616.

G. K. BAYDOĞMUŞ, “Detecting Internet of Things Attacks by Using Hybrid Learning and Feature Selection Method,” Eur. J. Sci. Technol., 2021, doi: 10.31590/ejosat.1017433.

F. S. Saadaari, D. Mireku-Gyimah, and B. Olaleye, “Development of a Stope Stability Prediction Model Using Ensemble Learning Techniques - A Case Study,” Ghana Min. J., vol. 20, no. 2, pp. 18–26, 2020, doi: 10.4314/gm.v20i2.3.

R. Mitra and T. Rajendran, “Efficient Prediction of Stroke Patients Using Random Forest Algorithm in Comparison to Support Vector Machine,” 2022, doi: 10.3233/apc220075.

H. Yıldırım, “Comparative Analysis of Machine Learning Algorithms Based on Variable Importance Evaluation,” J. Sci. Technol. Eng. Res., 2021, doi: 10.53525/jster.988672.

Z. P. Agusta and A. Adiwijaya, “Modified Balanced Random Forest for Improving Imbalanced Data Prediction,” Int. J. Adv. Intell. Inform., vol. 5, no. 1, p. 58, 2018, doi: 10.26555/ijain.v5i1.255.

L. Gao, M. Ye, and C. Wu, “Cancer Classification Based on Support Vector Machine Optimized by Particle Swarm Optimization and Artificial Bee Colony,” Molecules, vol. 22, no. 12, p. 2086, 2017, doi: 10.3390/molecules22122086.

S. Akin, M. Penner, and J. Peissig, “Joint Channel Estimation and Data Decoding Using SVM-based Receivers,” 2020, doi: 10.48550/arxiv.2012.02523.

J. J. M. Durango, C. González-Castaño, C. Restrepo, and J. Muñoz, “Application of Support Vector Machine to Obtain the Dynamic Model of Proton-Exchange Membrane Fuel Cell,” Membranes, vol. 12, no. 11, p. 1058, 2022, doi: 10.3390/membranes12111058.

S. Das, D. Tripathy, and J. L. Raheja, “A Review on Algorithms for EEG-Based BCIs,” pp. 25–56, 2018, doi: 10.1007/978-981-13-3098-8_3.

M. López-Pacheco and W. Yu, “Complex Valued Deep Neural Networks for Nonlinear System Modeling,” Neural Process. Lett., vol. 54, no. 1, pp. 559–580, 2021, doi: 10.1007/s11063-021-10644-1.

M. Pawlicki and R. S. Choraś, “Preprocessing Pipelines Including Block-Matching Convolutional Neural Network for Image Denoising to Robustify Deep Reidentification Against Evasion Attacks,” Entropy, vol. 23, no. 10, p. 1304, 2021, doi: 10.3390/e23101304.