Design and Implementation of Faculty Support System to Reduce Course Dropout Rates

Simple item page
dc.contributor.advisorEick, Christoph F.
dc.contributor.committeeMemberRizk, Nouhad
dc.contributor.committeeMemberTolar, Tammy
dc.contributor.committeeMemberShi, Weidong
dc.creatorJidagam, Rohith 1990-
dc.date.accessioned2018-07-10T18:51:43Z
dc.date.available2018-07-10T18:51:43Z
dc.date.createdMay 2016
dc.date.issued2016-05
dc.date.submittedMay 2016
dc.date.updated2018-07-10T18:51:43Z
dc.description.abstractThe primary goal of educational systems is not only to provide quality of education but also to make sure that students graduate with a strong academic standing. One specific challenge that universities face is high course drop rates. An early prediction of students’ failure may help to identify students who need special attention to reduce course drop rates by providing appropriate interventions, such as continuous mentoring and conducting review sessions. To address this problem, a new framework called Faculty Support System (FSS) is proposed that learns different classification models to predict student course performance based on his/her attendance, and performance in assignments, quizzes, in-class group projects, and exams. The investigated approaches for this task include Naïve Bayes, Multi-Layer Neural Networks, Decision Trees, and Random Forests. Next, using these models potentially low-performing students will be selected for interventions. Finally, data related to the performance of particular interventions and the employed classification models will be collected at the end of the semester. The proposed FSS framework is evaluated on two different real-world datasets that were obtained during two different semesters for two Computer Science courses at University of Houston, Texas. Our experimental results reveal that Multi-Layer Neural Networks performed the best, and the proposed modelling approach can efficiently identify students at risk, and recommend interventions to enhance their performance before the final exam of the semester. The evaluation of different classifiers on educational datasets gave some insights into how different data mining algorithms predict student performance and enhance student retention. Moreover, the experiments created valuable data about the performance of different interventions.
dc.description.departmentComputer Science, Department of
dc.format.digitalOriginborn digital
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/10657/3208
dc.language.isoeng
dc.rightsThe author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s).
dc.subjectEducational data mining
dc.subjectDecision trees
dc.subjectRandom forests
dc.subjectNaïve Bayes
dc.subjectMultiple Layer Neural Networks
dc.subjectClassification
dc.subjectStudent performance
dc.titleDesign and Implementation of Faculty Support System to Reduce Course Dropout Rates
dc.type.dcmiText
dc.type.genreThesis
thesis.degree.collegeCollege of Natural Sciences and Mathematics
thesis.degree.departmentComputer Science, Department of
thesis.degree.disciplineComputer Science
thesis.degree.grantorUniversity of Houston
thesis.degree.levelMasters
thesis.degree.nameMaster of Science

Files

Original bundle

Now showing 1 - 2 of 2
Thumbnail Image
Name:
JIDAGAM-THESIS-2016.pdf
Size:
1.29 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
Rohith_Thesis.docx
Size:
416.28 KB
Format:
Microsoft Word XML
Download

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.81 KB
Format:
Plain Text
Description:
Download

Collections

Published ETD Collection