Home Page > > Details

INFO411/911: Data Mining and Knowledge Discovery

Assignment 2 (15%)

Autumn 2022

Due 11:55 pm, Friday, 27 May 2022, via Moodle

Submit a single PDF document which contains your answers to the questions. All

questions are to be answered.

The PDF must contain typed text of your answer (do not submit a scan of a

handwritten document, any handwritten document will be ignored). The document

can include computer generated graphic (hand drawn graphic and illustrations will

be ignored).

Make sure you do the questions in order and use the following format when answer-

ing questions: R-code. R-output, and interpretations/calculations.

The PDF document of your answers should be no more than 20 pages including all

graphs. If it is over 20 pages, only the first 20 pages will be marked. The size limit

for this PDF document is 150MB.

Late submission will not be accepted without academic consideration being granted.

1

Questions

1. (3 marks) In this assignment we make use of the data creditworthiness.csv which

was used in Task 2 of Assignment 1. As before, we wish to predict the credit rating

that would be assigned to each individual. Recall that data on 2500 customers have

been collected, and credit rating for 1962 of them has been assessed as either A,

B, or C, coded as 1, 2, or 3, respectively, with the remaining 538 needing to be

classified. Write the code to split the dataset into 50% training set and 50% test

set and only include the data with known ratings.

2. Using default settings, fit a decision tree to the training set predict the credit ratings

of customers using all of the other variables in the dataset.

(a) (2 marks) Report the resulting tree.

(b) (2 marks) Based on this output, predict the credit rating of a hypothetical

“median” customer, i.e., one with the attributes listed in Table 1, showing the

steps involved.

(c) (2 marks) Produce the confusion matrix for predicting the credit rating from

this tree on the test set, and also report the overall accuracy rate.

(d) (5 marks) What is the numerical value of the gain in entropy corresponding

to the first split at the top of the tree? (Use logarithms to base 2, and show

the details of the calculation rather than just providing a final answer.)

(e) (2 marks) Fit a random forest model to the training set to try to improve

prediction. Report the R output.

(f) (2 marks) Produce the confusion matrix for predicting the credit rating from

this forest on the test set, and also report the overall accuracy rate.

3. Using default settings for svm() from the e1071 package, fit a support vector ma-

chine to predict the credit ratings of customers using all of the other variables in

the dataset.

(a) (2 marks) Predict the credit rating of a hypothetical “median” customer, i.e.,

one with the attributes listed in Table 1. Report decision values as well.

(b) (2 marks) Produce the confusion matrix for predicting the credit rating from

this SVM on the test set, and also report the overall accuracy rate.

(c) (2 marks) Automatically or manually tune the SVM to improve prediction

over that found in 3b. Report the resulting SVM settings and the resulting

confusion matrix for predicting the test set. (Any amount of improvement is

acceptable.)

4. Fit the Naive Bayes model to predict the credit ratings of customers using all of

the other variables in the dataset.

(a) (2 marks) Predict the credit rating of a hypothetical “median” customer, i.e.,

one with the attributes listed in Table 1. Report predicted probabilities as

well.

2

(b) (2 marks) Reproduce the first 20 or so lines of the R output for the Naive Bayes

fit, and use them to explain the steps involved in making this prediction.

(c) (2 marks) Produce the confusion matrix for predicting the credit rating using

Naive Bayes on the test set, and also report the overall accuracy rate.

5. Based on the confusion matrices reported in the preceding parts,

(a) (2 marks) Which of the classifiers look to be the best? (Be specific, and specify

the figures you used to answer this question.)

(b) (2 marks) Which look to be the worst? (Be specific, and specify the figures

you used to answer this question.)

(c) (2 marks) Are there any categories that all classifiers seem to have trouble

with?

6. Consider a simpler problem of predicting whether a customer gets a credit rating

of A or not.

(a) (2 marks) Fit a logistic regression model to predict whether a customer gets

a credit rating of A using all of the other variables in the dataset, with no

interactions.

(b) (2 marks) Report the summary table of the logistic regression model fit.

(c) (2 marks) Which predictors of credit rating appear to be significant at 5%

significance level?

(d) (2 marks) Fit an SVM model of your choice to the training set.

(e) (3 marks) Produce an ROC chart comparing the logistic regression and the

SVM results of predicting the test set. Comment on any differences in their

performance.

3

Table 1: Attributes of the median person in the credit-worthiness dataset.

functionary 0

re-balanced (paid back) a recently overdrawn current acount 1

FI3O credit score 1

gender 0

0. accounts at other banks 3

credit refused in past? 0

years employed 3

savings on other accounts 3

self employed? 0

max. account balance 12 months ago 3

min. account balance 12 months ago 3

avrg. account balance 12 months ago 3

max. account balance 11 months ago 3

min. account balance 11 months ago 3

avrg. account balance 11 months ago 3

max. account balance 10 months ago 3

min. account balance 10 months ago 3

avrg. account balance 10 months ago 3

max. account balance 9 months ago 3

min. account balance 9 months ago 3

avrg. account balance 9 months ago 3

max. account balance 8 months ago 3

min. account balance 8 months ago 3

avrg. account balance 8 months ago 3

max. account balance 7 months ago 3

min. account balance 7 months ago 3

avrg. account balance 7 months ago 3

max. account balance 6 months ago 3

min. account balance 6 months ago 3

avrg. account balance 6 months ago 3

max. account balance 5 months ago 3

min. account balance 5 months ago 3

avrg. account balance 5 months ago 3

max. account balance 4 months ago 3

min. account balance 4 months ago 3

avrg. account balance 4 months ago 3

max. account balance 3 months ago 3

min. account balance 3 months ago 3

avrg. account balance 3 months ago 3

max. account balance 2 months ago 3

min. account balance 2 months ago 3

avrg. account balance 2 months ago 3

max. account balance 1 months ago 3

min. account balance 1 months ago 3

avrg. account balance 1 months ago 3

Contact Us(Ghostwriter Service)

- QQ：99515681
- WeChat：codinghelp
- Email：99515681@qq.com
- Work Time：8:00-23:00

- Fit5217help With ,Python Programminghe... 2022-05-31
- Help With Ecs 170,Help With C++/Python... 2022-05-31
- Help With Ecs 170,Help With Python/C++... 2022-05-31
- Fit 5003Help With ,Help With Java/C++ ... 2022-05-30
- Help With Cse 101,Help With C/C++ Prog... 2022-05-30
- Help With Econ7150,Help With Java，Pyt... 2022-05-30
- Econ7150 Programminghelp With S1 202... 2022-05-29
- Cse 101 Programming Help With Data S... 2022-05-29
- Help With Fit 5003 Software Security 2022-05-29
- Stat7055 Introductory Statistics For B... 2022-05-28
- Assignment 3 Description: Computer Sy... 2022-05-28
- C++ Programminghelp With ,Help With Pr... 2022-05-28
- Help With Eece 1080C,C++ Programminghe... 2022-05-28
- Comp10002help With ,Help With C/C++ Pr... 2022-05-28
- Swen30006help With ,Help With Java/C++... 2022-05-28
- Comp326 Coursehelp With ,Help With Pyt... 2022-05-28
- C++ Programminghelp With ,Help With Da... 2022-05-27
- Help With Mast30025,R Programminghelp ... 2022-05-27
- Prog2002help With ,Help With Sql Progr... 2022-05-26
- Info411/911Help With ,Help With Java/P... 2022-05-26

Contact Us - Email：99515681@qq.com WeChat：codinghelp

© 2021 www.asgnhelp.com

Programming Assignment Help！