• Weighting: 30%
• Due date: Ongoing (Weeks 8–11 during Lab)
• Method of submission: Lab Presentation
• Content: Presentation (individual assessment)
• Length of submission: Presentation (12 minutes) + Q&A (2-3 minutes)

This assessment encourages students to expand and deepen their conceptual knowledge of big data in realworld applications (e.g., business, health). They achieve this through a discussion of a data analytics concept (e.g., big data frameworks, data visualization, natural language processing) in practice. In their presentation, students are required to provide evidence of extensive research on the concept, drawing from resources such as academic journals, professional press, and popular media. They are expected to demonstrate both reflection and analysis related to the chosen data analytics concept, and to produce a clear and concise response that conveys an evidence-based understanding of the topics.

In your presentation, we ask you to provide a practical case study on a specific big data analytics application. Each student (or group) will select their own data analytics project, identifying relevant data and a case study. The presentation should begin with an overview of the project, its significance, and the potential impact or applications it might have. Finding a suitable dataset and identifying relevant applications is a key part of this assessment. Students must outline interesting data science questions they aim to explore, address data quality issues, discuss data modeling approaches, identify key stakeholders, and present data visualisation or communication results.

1. Title Slide (1 slide: Project title and student names)

2. Datasets (1-2 slides: Background on the datasets and any data quality issues)

3. Case Study (1-2 slides: Specific application examples including interesting data science questions)

4. Data Modelling (1-2 slides: Data models and their suitability for the case study)

5. Data Visualisation/Communication of Results (1-2 slides: Appropriate data visualisation techniques to communicate results and support the project)

6. Preliminary Results (1-2 slides: Include data characterization, distribution, and initial data modelling results)

7. References (1-2 slides: Proper citation of data sources, articles, or other publications)