Reverse Migration Prediction Model Based on Machine Learning - Master of Science (Built Environment) Thesis

Aug 2, 2026

Reverse migration in Malaysia is an emerging pattern in which migrants intentionally return to their hometowns for better living conditions. Accurately forecasting migration is difficult due to the complexity and uncertainty of demographic change. This research applies machine learning to reduce prediction error and develop an effective reverse migration prediction model. Objectives include identifying determinants via systematic literature review, testing relationships using Shapiro-Wilk and Spearman correlation, and evaluating predictive performance using Random Forest, Decision Tree, and Gradient Boosted Tree. Results highlight six influential factors and show Random Forest achieves the best accuracy with lower classification error, supporting more efficient predictions aligned with Industrial 4.0.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages5

Reading Time13 min

AccessFree to download

Chapter 1 Introduction

1.1 Chapter Overview

1.2 Research Background

1.3 Problem Statement

1.4 Research Objectives and Research Aim

1.5 Research Question

1.6 Scope of Research

1.7 Research Phase

1.7.1 First Phase: Preliminary research

1.7.2 Second Phase: Literature Review

1.7.3 Third Phase: Data Collection

1.7.4 Fourth Phase: Data Analysis

1.7.5 Fifth Phase: Research Finding and Conclusion

1.8 Significance of Research

1.8.1 Significance for Practice

1.8.2 Theoretical Knowledge

1.8.3 Further Research

1.8.4 Novelty

1.9 Structure of Research

1.9.1 Chapter 1 : Introduction

UNIVERSITI TEKNOLOGI MARA REVERSE MIGRATION PREDICTION MODEL BASED ON MACHINE LEARNING AZREEN BINTI ANUAR Thesis submitted in fulfilment of the requirements for the degree of Master of Science (Built Environment) College of Built Environment March 2024 ABSTRACT Reverse migration in Malaysia is a relatively new emerging phenomenon where migrants intentionally choose to return to their hometown for better living. Thus, thereis a demand to investigate the determinants that lead to these changing population mobility trends in Malaysia. Migration predictions are notorious for bearing high error rate because migrations are the most complicated and unpredictable of the key demographic processes. A significant way to minimize the errors is by using a machine learning approach that can predict reverse migration intelligently depending on the tested dataset. Thus, this research aim to develop a reverse migration prediction model based on machine learning. To fulfil this aim, this research proposed three (3) objectives. The first objective is to identify the factors influencing reverse migration based on the statistics from previous empirical studies through a systematic literature review. The second objective to analyse the relationship among the factors that influence reverse migration in Malaysia using empirical experiments performed through the Shapiro-Wilk and Spearman Correlation analysis. And the third objective is to evaluate reverse migration prediction model based on machine learning analysis. For this purpose, three (3) algorithms have been assessed, namely, the Random Forest, Decision Tree, and Gradient Boosted Tree. The findings of this research have provided new insights into the six (6) factors that could influence reverse migration. In addition, the results from the three (3) algorithms that were tested showed that Random Forest outperforms other algorithms by acquiring an accuracy and classification error to predict reverse migration. With the application of machine learning aligned with Industrial 4.0, this research would be advantageous to predict reverse migration in a more efficient way. Keywords: Reverse Migration, Prediction Model, Machine Learning ACKNOWLEDGEMENT Firstly, I wish to thank God for giving me the opportunity to embark on my Master and for completing this long and challenging journey successfully. The greatest gratitude and thanks go to my supervisor Dr Nur Huzeima Mohd Hussain and co supervisor Assoc Prof Sr Dr Thuraiya Mohd and Associate Professor Dr Suraya Masrom. My appreciation goes to the Department of Statistics (DOSM) for providing me with the required data and information pertaining the reverse migration for my analysis. I would like to thank the IPSIS Department as Master Organizations, University of Technology MARA, or providing the facilities and equipment to finish this thesis. Special thanks to my colleagues and friends for their help, support, interest, and valuable hints for my research. Finally, this thesis is dedicated to my loving dear husband, for the consecutive supports throughout my Master journey. This piece of victory is dedicated to all of you. Alhamdulillah. TABLE OF CONTENTS Page CONFIRMATION BY PANEL OF EXAMINERS ii AUTHOR’S DECLARATION iii ABSTRACT iv ACKNOWLEDGEMENT v TABLE OF CONTENTS vi LIST OF TABLES x LIST OF FIGURES xii LIST OF ABBREVIATIONS xiii CHAPTER 1 INTRODUCTION 1 1.1 Chapter Overview 1 1.2 Research Background 1 1.3 Problem Statement 3 1.4 Research Objectives and Research Aim 4 1.5 Research Question 4 1.6 Scope of Research 5 1.7 Research Phase 5 1.7.1 First Phase: Preliminary research 7 1.7.2 Second Phase: Literature Review 7 1.7.3 Third Phase: Data Collection 7 1.7.4 Fourth Phase: Data Analysis 7 1.7.5 Fifth Phase: Research Finding and Conclusion 8 1.8 Significance of Research 8 1.8.1 Significance for Practice 8 1.8.2 Theoretical Knowledge 9 1.8.3 Further Research 9 1.8.4 No

FAQs

Why is predicting reverse migration challenging in Malaysia?

Reverse migration prediction faces high error because migration processes are complex and highly unpredictable demographic changes.

What machine learning algorithms were evaluated for the prediction model?

The study assessed Random Forest, Decision Tree, and Gradient Boosted Tree to predict reverse migration.

Which algorithm performed best and how is its performance described?

Random Forest outperformed the other algorithms, achieving better accuracy and lower classification error for reverse migration prediction.

Aug 2, 2026

Upload by Theodore