Description

Coursework (15% of Total Assessment)

This is an individual work.

Use student_performance.xlxs dataset for this assessment.

• gender – student’s sex (binary: ‘F’ – female or ‘M’ – male)
• age – student’s age (numeric: from 15 to 22)
• Medu – mother’s education (numeric: 0 – none, 1 – primary education (4th grade), 2 – primary education (5th to 9th grade), 3 – secondary education or 4 – higher education)
• Fedu – father’s education (numeric: 0 – none, 1 – primary education (4th grade), 2 – primary education (5th to 9th grade), 3 – secondary education or 4 – higher education)
• Mjob – mother’s job (nominal: ‘teacher’, ‘health’ care related, civil ‘services’ (e.g. administrative or police), ‘at_home’ or ‘other’)
• Fjob – father’s job (nominal: ‘teacher’, ‘health’ care related, civil ‘services’ (e.g. administrative or police), ‘at_home’ or ‘other’)
• studytime – weekly study time (numeric: 1 – <2 hours, 2 – 2 to 5 hours, 3 – 5 to 10 hours, or 4 – >10 hours)
• internet – Internet access at home (binary: yes or no)
• goout – going out with friends (numeric: from 1 – very low to 5 – very high)
• Dalc – workday alcohol consumption (numeric: from 1 – very low to 5 – very high)
• Walc – weekend alcohol consumption (numeric: from 1 – very low to 5 – very high)
• health – current health status (numeric: from 1 – very bad to 5 – very good)
• result – final grade (numeric: from 0 to 20, output target)

For modelling techniques, you must use Decision Tree and Regression, then select the best model. You can choose to build many different Decision Tree and Regression models with different parameters testing. Suggestion: build 7-10 models, then compare their performance to choose the best model.

Present your answer according to the requirements listed below, i.e., you DO NOT need to present other information other than the report content required as follows:

No. Content to Report
1. Data preparation: Which attributes you performed pre-processing? State your rationale. For each attribute you pre-processed, which method and how did you do it? NOTE: if you do not perform any data preparation, then just leave this section blank.

Present your answers in a tabular form as follows:

Attribute processed Rationale for processing Methods for processing

1/2

2. Present your modelling methods and the model performance in a tabular form as follows.

For example:
No. Modelling technique Partition ratio Other preparation methods applied Model performance
(misclassification /error)
1. Decision Tree
2. Decision Tree
3. Regression
4. Regression
….. ….. …..

3. Screenshot the Model Comparison Node’s Fit Statistics result using SAS Mining. For example:

4. Present the best model.

5. Interpret the best mode selected.

6. Present the screenshot of the whole modelling process diagram in SAS Miner.

Submission format:
• Include the above stated 6 requirements’ content into a PDF file (maximum 2 pages). Use your ID and name as the filename, for example, 11232612JohnSmith.pdf
• Submit through the eLearn portal.

2/2