Machine learning prediction for academic misconduct prediction - an analysis of binary classification metrics

Q: What problem does the study address regarding academic misconduct?

The study targets unethical academic misconduct and emphasizes the need for earlier-stage detection to enable more effective prevention in higher education institutions.

Q: Which machine learning algorithms are compared in predicting academic misconduct?

The study compares generalized linear model (GLM), logistic regression (LR), decision tree (DT), and random forest (RF) using binary classification metrics.

Q: How do demography and fraud triangle theory factors contribute to the models?

Fraud triangle attributes are identified as the most important predictors for GLM, LR, and DT through rationalization, while RF highlights opportunity as the most important. Demography attributes provide limited benefits across models, though they remain applicable with very low weight correlations.

Aug 3, 2026

Upload by Riley

Academic misconduct is unethical behavior in academic work, and early detection is essential for sustaining integrity culture in higher education. This study analyzes how machine learning can predict academic misconduct using binary classification performance metrics. Four algorithms—GLM, logistic regression, decision tree, and random forest—are compared, along with factor analysis based on demography attributes and fraud triangle theory. Results show >80% accuracy and <20% classification error rates, with fraud triangle rationalization most important in GLM/LR/DT and opportunity most important in RF.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Abstract

Keywords

Introduction

Bulletin of Electrical Engineering and Informatics Vol. 13, No. 1, February 2024, pp. 388~395 ISSN: 2302-9285, DOI: 10. 11591/eei.v13i1 .5629 􀂈 388 | Machine learning prediction for academic misconduct prediction: an analysis of binary classification metrics
Suraya Masrom1, Nor Hafiza Abdul Samad2, Ratna Septiyanti3, Nurshafinas Roslan2,
Rahayu Abdul Rahman4
1Computing Sciences Studies, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Perak Branch,
Malaysia
2Faculty of Computing and Multimedia, Universiti Poly-Tech Malaysia, Kuala Lumpur, Malaysia 3Faculty of Economics and Business, University of Lampung, Lampung, Indonesia
4Faculty of Accountancy, Universiti Teknologi MARA, Perak Branch, Malaysia | | | | --- | --- | --- | | Article Info | ABSTRACT | | | Article history:
Received Dec 26, 2022 Revised May 24, 2023 Accepted Jun 4, 2023
Keywords:
Academic misconduct Binary classification Demography
Fraud triangle theory Machine learning
Corresponding Author: | | Academic misconduct is unethical behavior in academic work. To sustain integrity culture and mitigating unethical conducts among higher education institutions community, the academic misconduct detection must be done atan earlier stage. Thus, this study attempted to provide a new empirical contribution with the analysis of binary classification performances metricsto describe the ability of machine learning in predicting academic misconduct. Four machine learning algorithms have been used namely generalized linear model (GLM), logistic regression (LR), decision tree (DT), and random forest (RF) . Beside performances comparison, this paper presents the analysis of academic misconduct factors that were constructed based on demography and fraud triangle theory (FTT) . The findings showed that all the four machine learning algorithms have obtained good ability in the prediction models with the accuracy at above 80% and below 20% of the classification errors. Rationalization from the FTT attributes has shown asthe most important factor in GLM, LR, and DT. In RF, opportunity of FTT attributes have become the most important. Compared to FTT attributes, demography attributes were not providing much benefits to all the machine learning models but remain applicable at very low weight correlations.
This is an open access article under the CC BY-SA license.
| | Rahayu Abdul Rahman
Faculty of Accounting, Universiti Teknologi MARA Perak Branch, Malaysia
Email: [rahay916@uitm.edu.my](rahay916@uitm.edu.my) | | | 1. INTRODUCTION Machine learning techniques have been utilized in the field of education for predicting academic misconduct [1]–[4] . Academic misconduct, usually referred to as academic dishonesty, is a global problem. Academic misconduct is defined as a purposeful fraud [5] as well as a specific form of regulation violation in higher education institutions [6] . Plagiarism, exam or test cheating, unauthorized collaboration, and fabrication are a few examples. Recently, incidents of academic misconduct become more prevalent due to the implementation of emergency remote teaching in curbing the spread of COVID-19 disease [7], which in turn raises the crucial need to use automated machine learning in academic misconduct prediction study in achieving more accurate outcomes. A review of literature documents various risk factors associated with the occurrence of academic misconduct such as personality traits [8], individual and situational factors [9], [10], ethical orientation [11], religiosity [12], and fraud theories factors [13] . Predicting academic misconduct is challenging but if the detection can be done at an earlier stage, then preventive measures can be taken more effectively at an earlier point of time. In the education domain, machine learning techniques play a major role in predicting various academic problems and issues such as student academic performance [14]–[16] and dropou

FAQs

What problem does the study address regarding academic misconduct?

The study targets unethical academic misconduct and emphasizes the need for earlier-stage detection to enable more effective prevention in higher education institutions.

Which machine learning algorithms are compared in predicting academic misconduct?

The study compares generalized linear model (GLM), logistic regression (LR), decision tree (DT), and random forest (RF) using binary classification metrics.

How do demography and fraud triangle theory factors contribute to the models?

Fraud triangle attributes are identified as the most important predictors for GLM, LR, and DT through rationalization, while RF highlights opportunity as the most important. Demography attributes provide limited benefits across models, though they remain applicable with very low weight correlations.

Aug 3, 2026

Upload by Riley