Predictive analytics in education- enhancing student achievement through machine learning

This study investigates the application of predictive analytics and machine learning models to enhance student achievement in educational settings. The experiment involved a dataset of 24,005 student records collected from institutional academic records at Wollo University and the Kombolcha Institut...

Full description

Saved in:
Bibliographic Details
Main Authors: Sunawar khan, Tehseen Mazhar, Tariq Shahzad, Muhammad Amir khan, Wajahat Waheed, Ahsen Waheed, Habib Hamam
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Social Sciences and Humanities Open
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590291125005522
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850039424910360576
author Sunawar khan
Tehseen Mazhar
Tariq Shahzad
Muhammad Amir khan
Wajahat Waheed
Ahsen Waheed
Habib Hamam
author_facet Sunawar khan
Tehseen Mazhar
Tariq Shahzad
Muhammad Amir khan
Wajahat Waheed
Ahsen Waheed
Habib Hamam
author_sort Sunawar khan
collection DOAJ
description This study investigates the application of predictive analytics and machine learning models to enhance student achievement in educational settings. The experiment involved a dataset of 24,005 student records collected from institutional academic records at Wollo University and the Kombolcha Institute of Technology, spanning the years 2017–2022. The data were systematically gathered from student demographic information, academic performance metrics, and contextual features such as studied credits, entrance results, and number of previous attempts. Unlike prior works, this study proposes a novel hybrid architecture that combines Convolutional Neural Networks (CNNs) and Random Forests with XGBoost as a meta-learner, achieving superior accuracy (88 %) compared to individual models such as Random Forest (85 %). Accuracy and other performance metrics (precision, recall, F1-score, and AUC-ROC) were calculated using a hold-out validation approach, with 80 % of the data used for training and 20 % for testing. This architecture effectively captures complex feature interactions and provides actionable insights for educators. Additionally, key predictive factors such as studied credits, entrance results, and regional differences were identified, offering a comprehensive understanding of student performance. The study addresses gaps in feature diversity and demonstrates the applicability of hybrid models in educational settings, paving the way for targeted interventions and improved resource allocation.
format Article
id doaj-art-cbff77b122e0484caabc9fdae0a20d62
institution DOAJ
issn 2590-2911
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Social Sciences and Humanities Open
spelling doaj-art-cbff77b122e0484caabc9fdae0a20d622025-08-20T02:56:21ZengElsevierSocial Sciences and Humanities Open2590-29112025-01-011210182410.1016/j.ssaho.2025.101824Predictive analytics in education- enhancing student achievement through machine learningSunawar khan0Tehseen Mazhar1Tariq Shahzad2Muhammad Amir khan3Wajahat Waheed4Ahsen Waheed5Habib Hamam6School of Computer Science, National College of Business Administration and Economics, Lahore 54000, PakistanSchool of Computer Science, National College of Business Administration and Economics, Lahore 54000, Pakistan; Department of Computer Science and Information Technology, School Education Department, Government of Punjab, Layyah 31200, Pakistan; Corresponding author.Department of Computer Engineering, COMSATS University Islamabad, Sahiwal Campus, Sahiwal, 57000, PakistanSchool of Computing Sciences, Faculty of Computer Science and Mathematics, Universiti Teknologi Mara, Shah Alam, 40450 Selangor, MalaysiaDepartment of Electrical and Computer Engineering, Purdue University, Indiana, 46323, USADepartment of Electrical and Computer Engineering, Purdue University, Indiana, 46323, USAFaculty of Engineering, Uni de Moncton, Moncton, NB, E1A3E9, Canada; International Institute of Technology and Management (IITG), Av. Grandes Ecoles, Libreville BP 1989, Gabon; College of Computer Science and Eng. (Invited Prof..), University of Ha'il, Ha'il 55476, Kingdom of Saudi Arabia; School of Electrical Engineering, University of Johannesburg, Johannesburg, 2006, South AfricaThis study investigates the application of predictive analytics and machine learning models to enhance student achievement in educational settings. The experiment involved a dataset of 24,005 student records collected from institutional academic records at Wollo University and the Kombolcha Institute of Technology, spanning the years 2017–2022. The data were systematically gathered from student demographic information, academic performance metrics, and contextual features such as studied credits, entrance results, and number of previous attempts. Unlike prior works, this study proposes a novel hybrid architecture that combines Convolutional Neural Networks (CNNs) and Random Forests with XGBoost as a meta-learner, achieving superior accuracy (88 %) compared to individual models such as Random Forest (85 %). Accuracy and other performance metrics (precision, recall, F1-score, and AUC-ROC) were calculated using a hold-out validation approach, with 80 % of the data used for training and 20 % for testing. This architecture effectively captures complex feature interactions and provides actionable insights for educators. Additionally, key predictive factors such as studied credits, entrance results, and regional differences were identified, offering a comprehensive understanding of student performance. The study addresses gaps in feature diversity and demonstrates the applicability of hybrid models in educational settings, paving the way for targeted interventions and improved resource allocation.http://www.sciencedirect.com/science/article/pii/S2590291125005522MLSVMCNNStudent achievementEducationLearning
spellingShingle Sunawar khan
Tehseen Mazhar
Tariq Shahzad
Muhammad Amir khan
Wajahat Waheed
Ahsen Waheed
Habib Hamam
Predictive analytics in education- enhancing student achievement through machine learning
Social Sciences and Humanities Open
ML
SVM
CNN
Student achievement
Education
Learning
title Predictive analytics in education- enhancing student achievement through machine learning
title_full Predictive analytics in education- enhancing student achievement through machine learning
title_fullStr Predictive analytics in education- enhancing student achievement through machine learning
title_full_unstemmed Predictive analytics in education- enhancing student achievement through machine learning
title_short Predictive analytics in education- enhancing student achievement through machine learning
title_sort predictive analytics in education enhancing student achievement through machine learning
topic ML
SVM
CNN
Student achievement
Education
Learning
url http://www.sciencedirect.com/science/article/pii/S2590291125005522
work_keys_str_mv AT sunawarkhan predictiveanalyticsineducationenhancingstudentachievementthroughmachinelearning
AT tehseenmazhar predictiveanalyticsineducationenhancingstudentachievementthroughmachinelearning
AT tariqshahzad predictiveanalyticsineducationenhancingstudentachievementthroughmachinelearning
AT muhammadamirkhan predictiveanalyticsineducationenhancingstudentachievementthroughmachinelearning
AT wajahatwaheed predictiveanalyticsineducationenhancingstudentachievementthroughmachinelearning
AT ahsenwaheed predictiveanalyticsineducationenhancingstudentachievementthroughmachinelearning
AT habibhamam predictiveanalyticsineducationenhancingstudentachievementthroughmachinelearning