Macquarie University
01whole.pdf (1.86 MB)

Prediction of acceptance of offers for academic places using data mining

Download (1.86 MB)
posted on 2022-03-29, 02:26 authored by Raj Man Shrestha
The thesis examines the validation of prediction models of acceptance of offers by students in the context and settings of international students in a large Australian University using data mining techniques. Earlier works in the enrolment management have examined various classification problems such as inquiry to enrolment, persistence, graduation using the data and the settings of a particular university. The data and settings from different institutions are often different which implies that, in order to find out which models and techniques are applicable at a given university, the dataset from that university needs to be used in the validation efforts. A dataset comprising the offers to students from a large Australian university where around 3,500 new international students commence their studies every year was analyzed. The important predictors for the acceptance of offers were the chosen course and the faculty, whether the student was awarded any forms of scholarship and also the visa assessment level of the country by immigration department. The prediction models were developed using logistic regression, decision trees and neural networks and their performances were compared. The prediction model by neural networks produced the best result.


Table of Contents

Chapter 1. Introduction -- Chapter 2. Background -- Chapter 3. Literature review -- Chapter 4. Data - descriptive analysis -- Chapter 5. Prediction models -- Chapter 6. Conclusions.


Theoretical thesis. Bibliography: pages 51-52

Awarding Institution

Macquarie University

Degree Type

Thesis MRes


MRes, Macquarie University, Faculty of Science and Engineering, Department of Computing

Department, Centre or School

Department of Computing

Year of Award


Principal Supervisor

Mehmet A. Orgun

Additional Supervisor 1

Peter Busch


Copyright Raj Man Shrestha 2014. Copyright disclaimer:






1 online resource (xvi, 52 pages) graphs, tables

Former Identifiers