A new framework in improving prediction of class imbalance for student performance in Oman educational dataset using clustering based sampling techniques

According to the Oman Education Portal (OEP), data set imbalances are common in student performance. Most of the students are performing welI, while only small cases of students are underperformed. Classification techniques for the imbalanced dataset can yield deceivingly high prediction accuracy. T...

Full description

Saved in:

Bibliographic Details
Main Author:	Sultan Alalawi, Sultan Juma
Format:	Thesis
Language:	eng eng
Published:	2021
Subjects:	L Education (General)
Online Access:	https://etd.uum.edu.my/10170/1/s902668_01.pdf https://etd.uum.edu.my/10170/2/s902668_02.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uum-etd.10170
record_format	uketd_dc
spelling	my-uum-etd.101702022-12-19T10:01:24Z A new framework in improving prediction of class imbalance for student performance in Oman educational dataset using clustering based sampling techniques 2021 Sultan Alalawi, Sultan Juma Mohd Shaharanee, Izwan Nizal Mohd Jamil, Jastini Awang Had Salleh Graduate School of Arts & Sciences Awang Had Salleh Graduate School of Arts & Sciences L Education (General) QA273-280 Probabilities. Mathematical statistics According to the Oman Education Portal (OEP), data set imbalances are common in student performance. Most of the students are performing welI, while only small cases of students are underperformed. Classification techniques for the imbalanced dataset can yield deceivingly high prediction accuracy. The majority class usually drives the overall predictive accuracy at the expense of having abysmal performance on the minority class. The main objective of this study was to predict students' performance which consisted of imbalanced class distribution, by exploiting different sampling techniques and several data mining classifier models. Three main sampling techniques - synthetic minority over-sampling technique (SMOTE), random under-sampling (RUS), and clustering-based sampling were compared to improve the predictive accuracy in the minority class while maintaining satisfactory overall classification performance. Five different data-mining classifiers - J48, Random Forest, K-Nearest Neighbour, Naïve Bayes, and Logistic Regression were used to predict the student performance. 10-fold cross-validation was utilized to minimize the sampling bias. The classifiers' performance was evaluated using four metrics: accuracy, False Positive (FP), Matthews correlation coefficient (MCC), and Receiver Operating Characteristic (ROC). The OEP datasets between 2018 and 2019 were extracted to assess the efficacy of both sampling techniques and classification methods. The results indicated that the K-Nearest Neighbors combined with the clustering-based sampling technique produced the best classification performance with an MCC value of 98.4% on the 10-fold crossvalidation. The clustering-based sampling techniques improved the overall prediction performance for the minority class. In addition, the most important variables to accurately predict student performance were identified by utilizing the Random Forest model. OEP contains a large amount of data and analyses based on this large and complex data can be useful for OEP stakeholders in improving student performance and identifying students who require additional attention. 2021 Thesis https://etd.uum.edu.my/10170/ https://etd.uum.edu.my/10170/1/s902668_01.pdf text eng 2024-12-07 staffonly https://etd.uum.edu.my/10170/2/s902668_02.pdf text eng public other doctoral Universiti Utara Malaysia
institution	Universiti Utara Malaysia
collection	UUM ETD
language	eng eng
advisor	Mohd Shaharanee, Izwan Nizal Mohd Jamil, Jastini
topic	L Education (General) L Education (General)
spellingShingle	L Education (General) L Education (General) Sultan Alalawi, Sultan Juma A new framework in improving prediction of class imbalance for student performance in Oman educational dataset using clustering based sampling techniques
description	According to the Oman Education Portal (OEP), data set imbalances are common in student performance. Most of the students are performing welI, while only small cases of students are underperformed. Classification techniques for the imbalanced dataset can yield deceivingly high prediction accuracy. The majority class usually drives the overall predictive accuracy at the expense of having abysmal performance on the minority class. The main objective of this study was to predict students' performance which consisted of imbalanced class distribution, by exploiting different sampling techniques and several data mining classifier models. Three main sampling techniques - synthetic minority over-sampling technique (SMOTE), random under-sampling (RUS), and clustering-based sampling were compared to improve the predictive accuracy in the minority class while maintaining satisfactory overall classification performance. Five different data-mining classifiers - J48, Random Forest, K-Nearest Neighbour, Naïve Bayes, and Logistic Regression were used to predict the student performance. 10-fold cross-validation was utilized to minimize the sampling bias. The classifiers' performance was evaluated using four metrics: accuracy, False Positive (FP), Matthews correlation coefficient (MCC), and Receiver Operating Characteristic (ROC). The OEP datasets between 2018 and 2019 were extracted to assess the efficacy of both sampling techniques and classification methods. The results indicated that the K-Nearest Neighbors combined with the clustering-based sampling technique produced the best classification performance with an MCC value of 98.4% on the 10-fold crossvalidation. The clustering-based sampling techniques improved the overall prediction performance for the minority class. In addition, the most important variables to accurately predict student performance were identified by utilizing the Random Forest model. OEP contains a large amount of data and analyses based on this large and complex data can be useful for OEP stakeholders in improving student performance and identifying students who require additional attention.
format	Thesis
qualification_name	other
qualification_level	Doctorate
author	Sultan Alalawi, Sultan Juma
author_facet	Sultan Alalawi, Sultan Juma
author_sort	Sultan Alalawi, Sultan Juma
title	A new framework in improving prediction of class imbalance for student performance in Oman educational dataset using clustering based sampling techniques
title_short	A new framework in improving prediction of class imbalance for student performance in Oman educational dataset using clustering based sampling techniques
title_full	A new framework in improving prediction of class imbalance for student performance in Oman educational dataset using clustering based sampling techniques
title_fullStr	A new framework in improving prediction of class imbalance for student performance in Oman educational dataset using clustering based sampling techniques
title_full_unstemmed	A new framework in improving prediction of class imbalance for student performance in Oman educational dataset using clustering based sampling techniques
title_sort	new framework in improving prediction of class imbalance for student performance in oman educational dataset using clustering based sampling techniques
granting_institution	Universiti Utara Malaysia
granting_department	Awang Had Salleh Graduate School of Arts & Sciences
publishDate	2021
url	https://etd.uum.edu.my/10170/1/s902668_01.pdf https://etd.uum.edu.my/10170/2/s902668_02.pdf
_version_	1776103757371670528

A new framework in improving prediction of class imbalance for student performance in Oman educational dataset using clustering based sampling techniques

Similar Items