Project 001: Victorian Travel Mode Choice Analysis

Python • Data Analysis • Statistics • Visualization • Team Project

Overview

We investigated whether household income influences travel mode choice among Victorian residents, based on survey data from a regional transport study.

Workflow: preprocessing → clustering → correlation analysis → supervised learning.

My Role (Team Lead)

Team leader (coordination, timeline, task allocation)
Implemented the Correlation Analysis component
Wrote most of the report content (main analysis sections)
Prepared and refined the presentation: rehearsal plan, content allocation, editing

Key Findings

Income shows very weak linear relationship with travel mode choice (Pearson near zero).
Clustering suggests coarse groupings, but with large overlap (not cleanly separable).
Baseline models (Logistic Regression / Decision Tree) achieve moderate accuracy but low macro-F1, indicating limited predictive signal using income alone.
Conclusion: income alone is insufficient; other demographic/geographic/accessibility factors likely matter more.

Report & Slides

You can read the full report below or download the files.

Download Report (PDF) Download Slides (PDF)

Project Report

Presentation Slides

Code

Code details are documented on the code page, including the pipeline and key excerpts.

Go to Code Page