BIG DATA DAN ANALITIK DATA S2 REGULER 29 [GDR]

Dashboard / My courses / FAKULTAS EKONOMI DAN BISNIS (FEB) / PRODI S2 MANAJEMEN (FEB) / 2324/1 / EMI1E3-S2 REGULER 29

/ Topik 5. Structured Data (Data Mining Model): Classification Model / Week 5 Quiz

Started on Monday, 13 November 2023, 6:47 PM

State Finished

Completed on Monday, 13 November 2023, 6:53 PM

Time taken 5 mins 48 secs

Marks 13.00/16.00

Grade 8.13 out of 10.00 (81%)

Question 1

Correct

Mark 1.00 out of 1.00

A method in classification that predict class attribute using C.45 algorithm is …..

Select one:

a. k-NN

b. Bayesian Method

c. Support Vector Machine

d. Decision Tree 

Good work

The correct answer is: Decision Tree

Incorrect

Mark 0.00 out of 1.00

Advantage of k-NN …

Select one:

a. All of the answer above are correct

b. Extremely flexible classification scheme 

c. Building model is cheap

d. Well suited for multi-modal classes

That's not correct

The correct answer is: All of the answer above are correct

Question 3

Correct

Mark 1.00 out of 1.00

Final decision in Random Forest method is chosen from…

Select one:

a. Decision of the majority of the trees 

b. Value of Gini Index

c. Decision of the last tree

d. Value of Entropy

Good work

The correct answer is: Decision of the majority of the trees

Correct

Mark 1.00 out of 1.00

High entropy means that the partitions in classification are

Select one:

a. useful

b. useless

c. not pure 

d. pure

Good work

The correct answer is: not pure

Question 5

Correct

Mark 1.00 out of 1.00

Measure of randomness in dataset is called as ….

Select one:

a. Lift

b. Information gain

c. Entropy 

d. Support

Good work

The correct answer is: Entropy

Correct

Mark 1.00 out of 1.00

Nearest neighbour method needs three things to perform its algorithm; dataset, value of k, and…

Select one:

a. Posterior probability

b. Class attribute

c. Entropy

d. Distance metric 

Good work

The correct answer is: Distance metric

Question 7

Incorrect

Mark 0.00 out of 1.00

One of disadvantage using decision tree method is …

Select one:

a. Slow at classifying unknown records

b. Expensive to construct

c. Hard to to interpret for small-sized trees 

d. The model can get unstable due to small variation of data

That's not correct

The correct answer is: The model can get unstable due to small variation of data
Question 8

Correct

Mark 1.00 out of 1.00

Ratio of number of correct decisions made and total number of decisions is called as …)

Select one:

a. Recall

b. Precision

c. Specificity

d. Accuracy 

Good work

The correct answer is: Accuracy

Question 9

Correct

Mark 1.00 out of 1.00

Recall or sensitivity equals to …

Select one:

a. TP / (TP + FN) 

b. TP / (TN + FN)

c. TP / (TN + FP)

d. TP / (TP + FP)

Good work

The correct answer is: TP / (TP + FN)

Incorrect

Mark 0.00 out of 1.00

Suppose that the confusion matrix is from testing the classifier on some test data. Which of the following situations
would you like your classifier to have?

Select one:

a. FN >> FP

b. FP >> FN

c. FN = FP × TP

d. TN >> FP 

That's not correct

The correct answer is: FP >> FN

Question 11

Correct

Mark 1.00 out of 1.00

The way to handle continuous attributes test with multi-way split is by …

Select one:

a. Discretization to form an ordinal categorical attribute 

b. All of the answer above are correct

c. Dividing values into two-subset

d. Directly use as many partitions as distinct values

Good work

The correct answer is: Discretization to form an ordinal categorical attribute

Correct

Mark 1.00 out of 1.00

There are total of 50 big data related articles in a repository of 200 articles) Suppose that a search engine retrieves 10
articles after a user enters 'big data' as a query, of which 5 are big data related articles) What are the precision and
recall?

Select one:

a. 50%; 20%

b. 50%; 10% 

c. 40%; 10%

d. 40%; 20%

Good work

The correct answer is: 50%; 10%

Question 13

Correct

Mark 1.00 out of 1.00

To measure the validity of a decision tree, we can use …

Select one:

a. Confusion matrix 

b. Distance metric

c. Entropy

d. Gini Index

Good work

The correct answer is: Confusion matrix

Correct

Mark 1.00 out of 1.00

Type of Data Mining model; for each individual in a population, predict a categorical label for some target; usually
comes with probability estimation or score

Select one:

a. Association

b. Clustering

c. Classification 

d. Regression

Good work

The correct answer is: Classification

Question 15

Correct

Mark 1.00 out of 1.00

What kind of model to predict data belong to specific group by giving specific label to the group?

Select one:

a. Clustering

b. Association Rules

c. Regression

d. Classification 

Good work

The correct answer is: Classification

Correct

Mark 1.00 out of 1.00

Which of the following statements about Naive Bayes is incorrect?

Select one:

a. Attributes can be nominal or numeric

b. Attributes are statistically dependent of one another given the class value. 

c. Attributes are equally important)

d. Attributes are statistically independent of one another given the class value.

Good work

The correct answer is: Attributes are statistically dependent of one another given the class value.

Previous Activity

Jump to...

Next Activity