Primary supervisor

Jesmin Nahar

 Title: Health and Social Challenges of Refugee Populations in Australia: A Data-Driven Investigation.

Keywords: Refugees, health outcomes, social challenges, data integration, policy analysis

Project Description:
Perform a comprehensive data-driven study on health and social challenges faced by refugee populations in Australia. The project integrates multiple datasets, applies advanced statistical analysis, and uses machine learning to detect patterns that inform policy and support services.

Objective:
To analyze and understand health and social factors affecting refugees to improve policy responses and support mechanisms.

Methods:

  • Multi-source data integration
  • Advanced statistical and exploratory analysis
  • Machine learning pattern recognition

Student cohort

Double Semester

Aim/outline

Aims

  • To identify key health and social challenges faced by refugee populations in Australia.
  • To detect patterns and risk factors using statistical and machine learning methods.
  • To generate evidence-based insights that can guide better policy and support services for refugees.

 Project Outline

  1. Data Integration: Collect and combine datasets from ABS, AIHW, and other public health/social sources.
  2. Exploratory & Statistical Analysis:
    • Descriptive statistics (health & social indicators).
    • Comparative tests (refugees vs non-refugees).
  3. Machine Learning Analysis:
    • Logistic Regression, Decision Trees, Random Forest, XGBoost to detect risk patterns (e.g., heart disease, mental health issues).
  4. Policy Implications: Translate findings into practical recommendations for refugee health and social support services.

Required knowledge

Required Knowledge for Students (for this project)

  1. Basic Statistics & Data Analysis

    • Understanding of descriptive statistics (mean, percentages, standard deviation).

    • Familiarity with hypothesis testing (t-tests, Chi-square).

  2. Programming & Data Handling

    • Basic knowledge of Python (pandas, seaborn, scikit-learn) or R (tidyverse) for data cleaning and analysis.

  3. Machine Learning Fundamentals

    • Basic understanding of supervised learning (Logistic Regression, Decision Trees).

    • Interest in learning more advanced methods (Random Forest, XGBoost).

  4. Health & Social Context Awareness (not mandatory but helpful)

    • Basic understanding of public health or social science concepts (mental health, housing, employment factors).

  5. Analytical & Critical Thinking

    • Ability to interpret results and link them to real-world policy or health challenges.