Beyond Performance: Explaining and Ensuring Fairness in Student Academic Performance Prediction with Machine Learning

This study addresses fairness in machine learning for student academic performance prediction using the UCI Student Performance dataset. We comparatively evaluate logistic regression, Random Forest, and XGBoost, integrating the Synthetic Minority Oversampling Technique (SMOTE) to address class imbal...

Full description

Saved in:
Bibliographic Details
Main Authors: Kadir Kesgin, Salih Kiraz, Selahattin Kosunalp, Bozhana Stoycheva
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/15/8409
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770936483446784
author Kadir Kesgin
Salih Kiraz
Selahattin Kosunalp
Bozhana Stoycheva
author_facet Kadir Kesgin
Salih Kiraz
Selahattin Kosunalp
Bozhana Stoycheva
author_sort Kadir Kesgin
collection DOAJ
description This study addresses fairness in machine learning for student academic performance prediction using the UCI Student Performance dataset. We comparatively evaluate logistic regression, Random Forest, and XGBoost, integrating the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance and 5-fold cross-validation for robust model training. A comprehensive fairness analysis is conducted, considering sensitive attributes such as gender, school type, and socioeconomic factors, including parental education (Medu and Fedu), cohabitation status (Pstatus), and family size (famsize). Using the AIF360 library, we compute the demographic parity difference (DP) and Equalized Odds Difference (EO) to assess model biases across diverse subgroups. Our results demonstrate that XGBoost achieves high predictive performance (accuracy: 0.789; F1 score: 0.803) while maintaining low bias for socioeconomic attributes, offering a balanced approach to fairness and performance. A sensitivity analysis of bias mitigation strategies further enhances the study, advancing equitable artificial intelligence in education by incorporating socially relevant factors.
format Article
id doaj-art-16b56cf9bedd4a77afa836b9266a87af
institution DOAJ
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-16b56cf9bedd4a77afa836b9266a87af2025-08-20T03:02:48ZengMDPI AGApplied Sciences2076-34172025-07-011515840910.3390/app15158409Beyond Performance: Explaining and Ensuring Fairness in Student Academic Performance Prediction with Machine LearningKadir Kesgin0Salih Kiraz1Selahattin Kosunalp2Bozhana Stoycheva3Department of Computer Technologies, Gönen Vocational School, Bandırma Onyedi Eylül University, 10250 Bandırma, Balıkesir, TürkiyeDepartment of Computer Technologies, Gönen Vocational School, Bandırma Onyedi Eylül University, 10250 Bandırma, Balıkesir, TürkiyeDepartment of Computer Technologies, Gönen Vocational School, Bandırma Onyedi Eylül University, 10250 Bandırma, Balıkesir, TürkiyeDepartment of Management and Social Activities, University of Ruse, 7017 Ruse, BulgariaThis study addresses fairness in machine learning for student academic performance prediction using the UCI Student Performance dataset. We comparatively evaluate logistic regression, Random Forest, and XGBoost, integrating the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance and 5-fold cross-validation for robust model training. A comprehensive fairness analysis is conducted, considering sensitive attributes such as gender, school type, and socioeconomic factors, including parental education (Medu and Fedu), cohabitation status (Pstatus), and family size (famsize). Using the AIF360 library, we compute the demographic parity difference (DP) and Equalized Odds Difference (EO) to assess model biases across diverse subgroups. Our results demonstrate that XGBoost achieves high predictive performance (accuracy: 0.789; F1 score: 0.803) while maintaining low bias for socioeconomic attributes, offering a balanced approach to fairness and performance. A sensitivity analysis of bias mitigation strategies further enhances the study, advancing equitable artificial intelligence in education by incorporating socially relevant factors.https://www.mdpi.com/2076-3417/15/15/8409student performance predictionlogistic regressionexplainable AI (XAI)SHAPfairness in educationadversarial debiasing
spellingShingle Kadir Kesgin
Salih Kiraz
Selahattin Kosunalp
Bozhana Stoycheva
Beyond Performance: Explaining and Ensuring Fairness in Student Academic Performance Prediction with Machine Learning
Applied Sciences
student performance prediction
logistic regression
explainable AI (XAI)
SHAP
fairness in education
adversarial debiasing
title Beyond Performance: Explaining and Ensuring Fairness in Student Academic Performance Prediction with Machine Learning
title_full Beyond Performance: Explaining and Ensuring Fairness in Student Academic Performance Prediction with Machine Learning
title_fullStr Beyond Performance: Explaining and Ensuring Fairness in Student Academic Performance Prediction with Machine Learning
title_full_unstemmed Beyond Performance: Explaining and Ensuring Fairness in Student Academic Performance Prediction with Machine Learning
title_short Beyond Performance: Explaining and Ensuring Fairness in Student Academic Performance Prediction with Machine Learning
title_sort beyond performance explaining and ensuring fairness in student academic performance prediction with machine learning
topic student performance prediction
logistic regression
explainable AI (XAI)
SHAP
fairness in education
adversarial debiasing
url https://www.mdpi.com/2076-3417/15/15/8409
work_keys_str_mv AT kadirkesgin beyondperformanceexplainingandensuringfairnessinstudentacademicperformancepredictionwithmachinelearning
AT salihkiraz beyondperformanceexplainingandensuringfairnessinstudentacademicperformancepredictionwithmachinelearning
AT selahattinkosunalp beyondperformanceexplainingandensuringfairnessinstudentacademicperformancepredictionwithmachinelearning
AT bozhanastoycheva beyondperformanceexplainingandensuringfairnessinstudentacademicperformancepredictionwithmachinelearning