Assessment Overview: Transport Data Science (TRAN5340M)

1 Objectives

This module’s assessments are designed to help you:

  1. Develop practical data science skills for solving real-world transport problems
  2. Apply programming and analysis techniques to transport datasets
  3. Generate insights from transport data that can inform policy and planning decisions
  4. Demonstrate reproducible research practices in transport studies

2 Module Assessment Structure

The module is assessed through two summative coursework assignments:

  1. Lab Notebook (CW1)
    • Worth 30% of module mark
    • Description: Data visualisation notebook with a data pipeline diagram showing input data sources and selected methods
    • Due: [TBC]
    • Length/format: [TBC]
  2. Report (CW2)
    • Worth 70% of module mark
    • Description: Report describing the use of data science to answer a transport planning related research question or applied problem
    • Due: [TBC]
    • Length/format: [TBC]

3 File Naming Convention

You must name your files using the following format:

TRAN5340M_StudentIDNumber.file_type

For example: - TRAN5340M_201234567.zip

4 Submission Format Requirements

4.1 Document Formatting

  • Include student ID in the title page
  • Do not include your name (for anonymous marking)
  • Use the default Quarto referencing style

4.2 File Requirements

Lab Notebook Package: - PDF report (max 4 pages) - Reproducible code (.qmd file) - Maximum .zip file size: [TBC]

Report Package: - PDF report ([TBC] page/word limits) - Reproducible code (.Rmd or .qmd file) - Maximum .zip file size: [TBC]

5 Submission Process

  1. Prepare Your Submission
    • Ensure correct file naming
    • Check formatting requirements
    • Test code reproducibility
    • Verify file sizes
  2. Submission: Via Minerva (Blackboard Assignment)
    • Deadline is 14:00 on submission day
    • Each assignment has its own submission point
    • Keep submission confirmation

6 Marking Criteria

6.1 Assessment Criteria

Detailed criteria and rubrics are provided in the assessment briefs:

7 Important Notes

7.1 Topic Selection

  • Topics should address real transport planning/policy challenges
  • The module team can provide guidance on topic selection
  • Guidance on topics and datasets is provided in module documents and assessment briefs

7.2 Use of AI Tools

Both assessments are categorized as GREEN for AI usage: - AI tools actively encouraged for coding and problem-solving - Usage should be documented in reflective sections - You must understand and be able to explain all submitted work - Critical evaluation of AI outputs is expected - AI will not be used to assess the submissions.

7.3 Academic Integrity

  • All work must meet university standards
  • Proper referencing required
  • Plagiarism checks applied through Turnitin

8 Support Available

  1. Academic Support
    • Module team can be contacted via email
    • Weekly sessions
  2. Technical Support
    • Code templates and examples provided in the course website
    • R/RStudio guidance
    • Data access support
  3. Writing Support

9 Key Dates (2027-28)

  • [TBC]: Lab Notebook (CW1)
  • [TBC]: Report (CW2)
  • Feedback provided within 15 working days

10 Assessment Checklist

10.1 For Both Submissions

10.2 Additional for Report