Coursework submission 2: Data science project report

1 Overview

This is the final assessed coursework submission for the Transport Data Science module. The deadline is 16th May 2025, 14:00.

The purpose of the coursework is to provide a professional-quality report on the data science project you have worked on. You should include a range of techniques and methods you have learned during the module, and apply them to a real-world transport problem. The project report should be a cohesive whole, however, not a disjointed portfolio of separate tasks.

A good way to think about the project report is to imagine that you have worked on an important data science project in a large organisation and you are presenting your findings with a view to impressing them with your skills, clearly communicating your results, and providing actionable insights that motivate change.

2 Key Requirements

  • Length: Maximum 10 pages (excluding the coversheet, references, acknowledgements and appendices)
    • See the template in the course GitHub repository at github.com/itsleeds/tds in folder/file d2/template.qmd, which includes the coversheet
  • Word count: Maximum 3,000 words (excluding tables, code, references, and captions)
  • Format: Submit both a PDF file and the source .qmd file in a .zip file
  • File size: Maximum 40 MB for the .zip file
  • Submission: Via Minerva (Turnitin)

3 Report Structure

Your report should have a logical structure and clear headings which could include:

  1. Introduction
    • Clear research question
    • Context and motivation
    • Reference to relevant literature
  2. Input Data and Data Cleaning
    • Description of datasets
    • Data quality considerations
    • Processing steps
  3. Exploratory Data Analysis
    • Initial visualization
    • Key patterns
    • Statistical summaries
  4. Analysis and Results
    • Detailed analysis
    • Clear presentation
    • Supporting visualizations
  5. Discussion and conclusions
    • Result, key findings, interpretation
    • Policy implications/recommendations
    • Strengths and limitations
    • Future directions
  6. References
    • Properly formatted citations
    • Mix of academic and technical/policy/other sources
    • Recommendation: generate these with Quarto (see Quarto Citation Guide)

4 Assessment Criteria

Marks will be awarded based on the marking criteria outlined in the marking criteria document.

5 Technical Requirements

6 Academic Integrity

  • Clearly acknowledge any use of AI tools (AMBER category)
  • Properly cite all sources
  • Include original data processing and analysis work
  • Document any collaboration or assistance received

For questions or clarifications, please use the module Teams channel or contact the module leader.