7CS512 Business Analytics Coursework 2 Assessment Brief 2026 | University of Derby
7CS512 Business Analytics CW2 Assessment BriefÂ
Description of the Assessment
This coursework is an individual assessment that requires you to design and implement a complete business analytics solution using a real-world dataset.
You will carry out all data preparation and analytics using Python, followed by the creation of a dashboard using either Power BI or Tableau. The aim is to demonstrate your ability to generate analytical insights using different tools and to communicate those insights effectively.
The assessment reflects the full analytics lifecycle covered in the module, from data acquisition and preparation to analysis, visualisation, and interpretation of results.
Assessment Content
You are required to design and implement a business analytics solution for a real-world dataset.
Dataset Selection
You must select a real-world dataset that is suitable for business analytics.
Your chosen dataset must be approved by the module leader before you begin your analysis.
Project Deliverables and Required Structure
The following sections outline the expected components of your submission and guide how your work should be structured.
1. Problem Context and Objectives
- Description of the business context
- Definition of the problem or question being addressed
- Clear analytical objectives
2. Data Acquisition and Preparation (Python)
- Description of the dataset and data source
- Data quality issues and preparation steps
- Data cleaning, transformation, and structuring using Python
3. Analytics Techniques and Modelling (Python)
- Application of appropriate statistical and machine learning techniques
- Justification for the chosen methods
- Explanation of how the techniques address the analytical objectives
4. Visualisation and Dashboard Development
- Visualisation of results generated through statistical and machine learning analysis in Python
- Development of a dashboard using Power BI or Tableau
- Clear presentation of analytical findings
5. Critical Reflection
- Evaluation of the quality and limitations of the analytics solution
- Discussion of assumptions, constraints, and potential improvements
- Ethical, legal, or governance considerations where relevant
Technical Tool Requirements
All data preparation, analysis, and modelling must be carried out using Python.
The analysis must be implemented and presented in a Jupyter Notebook, which is the required format for this assessment.
In addition, you must create a dashboard using either Power BI or Tableau based on the results generated in Python.
The notebook must be:
- Clearly structured
- Well commented where appropriate
- Reproducible
- Easy to follow for a third party
Demonstration Requirements
You are required to provide a demonstration of your analytics solution.
The demonstration schedule will be finalised during Weeks 10 and 11.
The demonstration will take place after the final submission.
Assessment Rubric
| Component | Criterion | Excellent (70–100%) | Merit (60–69%) | Good (50–59%) | Almost (40–49%) | Unsatisfactory (0–39%) |
|---|---|---|---|---|---|---|
| Python | Problem context and analytical objectives (5) | Clear and well-defined business context with focused and relevant analytical objectives. For 80% and above: objectives demonstrate strong analytical focus and strategic relevance. | Clear context and objectives, though focus may be uneven. | Context and objectives identified but lack clarity or focus. | Limited or unclear context and objectives. | No clear business context or objectives. |
| Python | Data acquisition and preparation (15) | Data is appropriately sourced, thoroughly cleaned, transformed, and well prepared using Python. For 80% and above: data preparation is robust, efficient, and well justified. | Data preparation is appropriate with minor issues or limited justification. | Basic data preparation completed but lacks depth or consistency. | Limited or weak data preparation. | Data preparation is missing or incorrect. |
| Python | Analytics techniques and modelling (15) | Appropriate statistical and machine learning techniques are correctly implemented and justified. For 80% and above: techniques are applied rigorously with strong analytical judgement. | Appropriate techniques applied with reasonable justification. | Techniques applied but with limited justification or technical issues. | Limited or inappropriate techniques used. | Techniques are missing or incorrectly applied. |
| Python | Interpretation of analytical results (15) | Results are clearly interpreted and linked to the analytical objectives. For 80% and above: interpretation demonstrates clear analytical reasoning. | Results are interpreted with reasonable clarity. | Basic interpretation provided, but lacks depth. | Limited or unclear interpretation. | No meaningful interpretation provided. |
| Python | Code quality, structure, and reproducibility (5) | Code is well structured, readable, and reproducible within a Jupyter Notebook. For 80% and above: code demonstrates professional quality and best practice. | Code is generally clear and reproducible with minor issues. | Code runs, but the structure or clarity is inconsistent. | The code is poorly structured or difficult to follow. | Code is incomplete, non-functional, or missing. |
| Dashboard | Dashboard design and analytical alignment (20) | Dashboard clearly reflects results generated in Python and communicates insights effectively. For 80% and above: dashboard design demonstrates excellent analytical alignment and data communication practice. | Dashboard reflects analytical results with reasonable clarity. | Dashboard is present but weakly linked to analysis. | The dashboard is limited or poorly aligned with the analysis. | Dashboard is missing or not based on analysis. |
| Demonstration | Explanation, insight, and understanding (25) | Demonstration clearly explains the analytics solution, dashboard, and insights with confidence. For 80% and above: explanation shows deep understanding, critical insight, and full ownership of the work. | Clear explanation of the solution with a good understanding. | Adequate explanation but limited depth or clarity. | Weak explanation with gaps in understanding. | Unable to explain or justify the work presented. |