Weighting: 35%Total marks: 95
MA5832-Assessment 2
Weighting: 35%Total marks: 95
Overview
In this assessment, you will implement and compare three machine learning algorithms on a real data. The assessment addresses the following learning outcome(s):
identifying and translating a data science problem into a supervised learning problem;identifying appropriate lasso-regression, tree-based methods, and support vector classification for descriptive problems;application of lasso-regression, support vector classifier and tree-based methods covered in Week 1, 3 and 4 to a dataset using the computer language R and the software environment RStudio.
Submission
You will need to submit the following:
A PDF file clearly shows the assignment question, the associated answers, any relevant R outputs, analyses and discussions. Please attach R code script in Appendix.
Rmarkdown/R script file to reproduce your work.
The task cover sheet
You have up to three attempts to submit your assessment, and only the last submission will be graded.
A word on plagiarism:
Plagiarism is the act of using anothers words, works or ideas from any source as ones own, this includes the use of large language model, such as ChatGPT. Plagiarism has no place in a University. Student work containing plagiarised material will be subject to formal university processes.
Problem(75 marks)
Background on Credit Card Dataset
The data, CreditCard Data.xls, is based on Yeh and Lien (2009). The data contains 30,000 observations and 23 explanatory variables. The response variable, Y, is a binary variable where 1 refers to default payment and 0 implies non-default payment. The description of 23 explanatory variables is as follows:
X1: Amount of the given credit (NT dollar): it includes both the individual consumer credit and his/her family (supplementary) credit.
X2: Gender (1 = male; 2 = female).
X3: Education (0 = unknown; 1 = graduate school; 2 = university; 3 = high school; 4 = others; 5 = unknown; 6 = unknown).
X4: Marital status (0 = unknown; 1 = married; 2 = single; 3 = others).
X5: Age (year).
X6 - X11: History of past payment. The data was tracked the past monthly payment records (from April to September, 2005) as follows: X6 = the repayment status in September, 2005; X7 = the repayment status in August, 2005; . . .;X11 = the repayment status in April, 2005. The measurement scale for the repayment status is: -2= no consumption, -1=pay duly, 0 = the use of revolving credit; 1 = payment delay for one month; 2 = payment delay for two months; . . .; 8 = payment delay for eight months; 9 = payment delay for nine months and above.
X12-X17: Amount of bill statement (NT dollar). X12 = amount of bill statement in September, 2005; X13 = amount of bill statement in August, 2005; . . .; X17 = amount of bill statement in April, 2005.
X18-X23: Amount of previous payment (NT dollar). X18 = amount paid in September, 2005; X19 = amount paid in August, 2005; . . .;X23 = amount paid in April,
2005.
Assessment Tasks
Data
(a) Select a random sample of 70% of the full dataset as the training data, retain the rest as test data. Provide the code and print out the dimensions of the training data.
Lasso regression
Use lasso-regression to find the best model which classifies credible and non-credible clients. Specify any underlying assumptions. Justify your model choice as well as hyper-parameters which are required to be specified in R. (10 marks)
Display model summary and discuss the relationship between the response variable versus selected features.(10 marks)
Evaluate the performance of the algorithm on the training data and comment on the results.(5 marks)
Tree Based Algorithms
Use an appropriate tree based algorithm to classify credible and non-credible clients. Specify any underlying assumptions. Justify your model choice as well as hyperparameters which are required to be specified in R. (10 marks)
Display model summary and discuss the relationship between the response variable versus selected features.(10 marks)
Evaluate the performance of the algorithm on the training data and comment on the results.(5 marks)
Support vector classifier
Use an appropriate support vector classifier to classify the credible and non-credible clients. Justify your model choice as well as hyper-parameters which are required to be specified in R.(10 marks)
Display model summary and discuss the relationship between the response variable versus selected features.(10 marks)
Evaluate the performance of the algorithm on the training data and comment on the results.(5 marks)
Prediction
Apply your the optimal models identified in section , and make prediction on the test data. Evaluate the performance of the algorithms on test data. Which models do you prefer? Are there any suggestions to further improve the performance of the algorithms?
Justify your answers.(20 marks)
References
Yeh, I.-C. and Lien, C.-h. (2009). The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Expert systems with applications, 36(2):24732480.
Assessment 2: Shrinkage method, Regression trees and Support vector machines
Top of Form
Bottom of Form
Assignment Content
Top of Form
Overview
In this assessment, you will implement and compare three machine learning algorithms on a real data.
Aligned learning outcomesThis assessment addresses the following learning outcome(s):
identifying and translating a data science problem into a supervised learning problem;identifying appropriate tree-based methods, and support vector classification for descriptive problems;application of lasso-regression, support vector classifier and tree-based methods covered in Week 1, 3 and 4 to a dataset using the computer language R and the software environmentSubmission
You will need to submit the following:
A PDF file clearly shows the assignment question, the associated answers, any relevant R outputs, analyses and discussions. Please also attach R code script in Appendix.Submissions where the code or text is given as an image or screen capture will not be accepted. Codemustbe given as text.
Rmarkdown/Rscript file to reproduce your work. Submissions where the code or text is given as an image or screen capture will not be accepted. Codemustbe given as text.
The task cover sheet.
You have up to three attempts to submit your assessment, and only the last submission will be graded.
A word on plagiarism
Plagiarism is the act of using anothers words, works or ideas from any source as ones own. Plagiarism has no place in a University. Student work containing plagiarised material will be subject to formal university processesPlease download the PDF files and dataset used in Assessment 2.
MA5832_Assessment2.pdf
CreditCard_Data.xls
Assessment declaration
By submitting this piece of assessment electronically, I declare that:
This assignment is my original work and no part has been copied/reproduced from any other persons work or from any other source, except where acknowledgement has been made.
This work has not been submitted previously for assessment and received a grade, nor concurrently for assessment, either in whole or part, for this subject (unless part of integrated assessment design/approved by the Subject Coordinator), any other subject or any other course.
Bottom of Form
