COM6013 Data Mining Portfolio Assessment Brief 2026 | Arden University

COM6013 Assessment Brief

Learning outcomes (LOs): The skills and knowledge that you should be able to show in your work.

Rubric/Marking Matrix: A set of rules or guidelines used to grade or assess work.

Task summary:

This assessment contains 2 different tasks:

• Task 1: Build a data mining model using python.
• Task 2: Write a comprehensive report.

Each task has its own mark weighting and submission format that must be adhered to.

Assignment instructions:

Your assignment should include: a title page containing your student number, the module name, the submission deadline and the exact word count of your submitted document; the appendices if relevant; and a reference list in AU Harvard system(s). You should address all the elements of the assignment task listed below. Please note that tutors will use the assessment criteria set out below in assessing your work.
You must not include your name in your submission because Arden University operates anonymous marking, which means that markers should not be aware of the identity of the student. However, please do not forget to include your STU number

Ensure that the specification document is saved in the following file name/format: [yourstudentnumber]_dm_report.docx /pdf
e.g. STU123456_dm_report.docx/pdf

Scenario:

You are working as a Junior Data Analyst at Medical Investigations Ltd., a consultancy that supports public health authorities in improving medical outcomes through data science.

Your team has been approached by the North Health Authority (NHA), which seeks to understand factors influencing cancer patient survival rates. The NHA has provided a dataset containing relevant patient information. Your task is to perform a classification analysis using Python to identify patterns that could assist in medical decision-making and patient care strategies.

Task 1

You have been assigned to conduct a data investigation focusing on patient survival prediction. The Chief Data Investigator has asked you to develop and evaluate several classification models to determine which is most accurate and reliable.

The project should include the following sections:

• Data pre-processing.
• Exploratory data analysis (EDA).
• Build multiple classification models.
• Evaluate models using appropriate metrics.
• Identify and justify the best-performing model.
• Present the complete investigation written in Python. 

(70 marks)
(LO’s: 1 & 3)
(Equivalent to 2800 words)

Task 2

Based upon the completed data mining investigation in Task 1, you will now write a comprehensive report that can be easily understood by the North Health Authority’s higher management team, so appropriate action can be taken in the future.

Requirements

Contained within your report, you will include:

• An evaluation and comparison of all classification models tested.
• A clear justification for your chosen final model.
• Discussion of key insights and limitations of your analysis.
• Conclusions and recommendations for the health authority’s next steps.

(30 marks)
(LO’s: 2 & 4)
(1200 words)