Please use this identifier to cite or link to this item: https://bspace.buid.ac.ae1234/1254
Title: Mining Student Information System Records to Predict Students’ Academic Performance
Authors: ABU SAA, AMJED TARIQ MOHAMMAD
Keywords: data mining techniques
student information system records
academic performance
United Arab Emirates (UAE)
Educational Data Mining (EDM)
Issue Date: Nov-2018
Publisher: The British University in Dubai (BUiD)
Abstract: An increasing interest has arisen during the past decade to identify the most important factors influencing students’ performance in higher education, especially by using predictive data mining techniques. This field of research is usually identified as educational data mining. Educational Data Mining (EDM) is the field of study that is concerned about mining useful patterns and predicting student’s academic performance in the field of education. Researchers in this field tend to study different types of students’ factors and attributes that affect their performance and learning outcomes. In this dissertation, 36 research articles out of a total of 420 from 2009 to 2018 were critically reviewed and analyzed by applying a systematic literature review approach. As well as, this dissertation provides a predictive data mining study targeted towards the use of student information systems’ data to predict students’ academic performance. A gap between student information systems and data mining was identified and addressed in this study, which suggests connecting both worlds together creating an intelligent system that is capable to predict student’s failures and low academic performance according to relevant students’ attributes. The main aim of this study is to identify the most commonly studied factors that affect the students’ performance, as well as, the most common data mining techniques applied to identify these factors. Accordingly, this dissertation generated a dataset from a student information system from a local university in the United Arab Emirates. The dataset included 34 attributes of student’s related information, and was having a data size of more than 56,000 records. Empirical results showed that four types of student attributes are responsible for academic performance prediction, including, students’ demographics, students’ previous performance information, course and instructor information as well as some student general information. Additionally, the results also indicated that the most common data mining techniques used to predict and classify students’ factors are decision trees, Naïve Bayes, and artificial neural networks. Finally, a set of data-mining models was compared in order to identify the most suitable one for predicting students’ academic performance from student information systems. Keywords: Educational Data Mining; students’ factors; students’ academic performance; systematic review; data mining techniques; student information systems.
URI: https://bspace.buid.ac.ae1234/1254
Appears in Collections:Dissertations for Informatics (Knowledge and Data Management)

Files in This Item:
File Description SizeFormat 
2015110088.pdf1.24 MBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.