DATA MINING
ASSIGNMENT 0
==================================================
Q1) Which of the following software is used to store and manage data in large enterprises:
A) Database Management System
B) Computer Networks
C) Operating System
D) Compiler
Q2) The most common form of Database Management System is:
A) Transitional
B) Rotational
C) Relational
D) Translational
Q3) Data Mining is valuable to an enterprise for:
A) Finding patterns and trends
B) Security
C) Communication
D) Human Resource
Q4) Data Mining is also commonly known as:
A) Web Searching
B) Data Scrapping
C) Data Transfer
D) Knowledge Discovery in Database
Q5) On what kind of data can data mining algorithms be applicable:
A) Video
B) Text
C) Image
D) All of the above
Q6) Which of the following applications involve classification?
A) Identifying Similar Households based on Electricity Consumption
B) Predicting Price of Rice Next Year
C) Identifying Supermarket Items Commonly Bought Together
D) Detecting Fraud Users of a Credit Card
Q7) Which of the following applications involve clustering?
A) Identifying Similar Households based on Electricity Consumption
B) Predicting Price of Rice Next Year
C) Identifying Supermarket Items Commonly Bought Together
D) Detecting Fraud Users of a Credit Card
Q8) For which of the following tasks can we use Regression?
A) Identifying Similar Households Based on Electricity Consumption
B) Predicting Price of Rice Next Year
C) Identifying Supermarket Items Commonly Bought Together
D) Detecting Fraud Users of a Credit Card
Q9) For which of the following we can use Association Rules?
A) Identifying Similar Households Based on Electricity Consumption
B) Predicting Price of Rice Next Year
C) Identifying Supermarket Items Commonly Bought Together
D) Detecting Fraud Users of a Credit Card
Q10) Data Mining may involve analysis of:
A) large Volume of Data
B) Heterogeneous Data
C) Dynamic Data
D) All of the Above
Data Mining
Assignment 1
All Questions are of 1 mark.
1.
a)
b)
c)
d)
Which of the following is usually the last step in the data mining process?
Visualization
Preprocessing
Modelling
Deployment
Ans: d
Explanation: The last step in the data mining process is to deploy the models to a production
environment. Deployment is important because it makes the models available to users for use.
2.
a)
b)
c)
d)
Sales database of items in a supermarket can be considered as an example of:
Record data
Ordered data
Graph data
None of the above
Ans: a
Explanation: The most basic form of record data has no explicit relationship among records or
data fields, and every record (object) has the same set of attributes. Record data is usually
stored either in flat files or in relational databases.
3.
a)
b)
c)
d)
HTML links are an example of:
Record data
Ordered data
Graph data
None of the above
Ans: c
Explanation: HTML links are an example of graph data.
4.
a)
b)
c)
d)
Name of a place, can be considered an attribute of type?
Nominal
Ordinal
Interval
Ratio
Ans: a
Explanation: Nominal‐related to names. The values of a Nominal attribute are name of things,
some kind of symbols. There is no order (rank, position) among values of nominal attribute.
5.
a)
b)
c)
A store sells 10 items. Maximum possible number of candidate 3‐itemsets is:
120
6
15
d) 56
Ans: a
Explanation: Number of ways of choosing 3 items from 10 items is 10C3 = 120
6. If a record data matrix has reduced number of columns after a transformation, the
transformation has performed:
a) Data Sampling
b) Dimensionality Reduction
c) Noise Cleaning
d) Discretization
Ans: b
Explanation: Dimensionality reduction is the process of reducing the number of random variables
under consideration, by obtaining a set of principal variables.
Answer Q7‐Q10 based on the following table:
Transaction ID
1
2
3
4
5
6
7.
a)
b)
c)
d)
Itemsets
{1, 2, 4, 5}
{2, 3, 5}
{1, 2, 4, 5}
{1, 2, 3, 5}
{1, 2, 3, 4, 5}
{2, 3, 4}
Support of rule {4,5} ‐> {1}
1
0.5
0.25
0
Ans: b
Explanation: support of X ‐> Y is support({X,Y})/|T| = 3/6 = 0.5.
8.
a)
b)
c)
d)
confidence of rule {4,5} ‐> {1} is:
1
0.5
0.25
0.75
Ans: a
Explanation: Confidence measures the occurrence of products together in a dataset.
Confidence(X‐>Y) = support({X,Y})/support({X})=(3/6)/(3/6)=1.
9.
a)
b)
c)
d)
Support of {1} ‐> {2,5} is:
2/3
2/2
1/4
3/4
Ans: a
Explanation: support of X ‐> Y is support({X,Y})/|T| = 4/6 = 2/3.
10.
a)
b)
c)
d)
Confidence of {1} ‐> {2,5}
2/3
1
0
0.5
Ans: b
Explanation: Confidence measures the occurrence of products together in a dataset.
Confidence(X‐>Y) = support({X,Y})/support({X})=(4/6)/(4/6)=1.
Data Mining: Assignment Week 2
1. If a store has N items, the number of possible itemsets is:
A. 2N‐1
B. 2N‐1
C. N/2
D. N‐1
2. An association rule is valid if it satisfies:
A. Support criteria
B. Confidence criteria
C. Both support and confidence criteria
D. None of the above
3. An itemset is frequent if it satisfies the:
A. Support criteria
B. Confidence criteria
C. Both support and confidence criteria
D. None of the above
4. Which of the following property is used by the apriori algorithm:
A. Positive definiteness property of support
B. Positive semidefiniteness property of support
C. Monotone property of support
D. Antimonotone property of support
5. Consider three itemsets I1={bat, ball, wicket}, I2={bat, ball}, I3={bat}. Which of the following statements
are correct?
A. support(I1) > support(I2)
B. support(I2) > support(I3)
C. both statements A and B
D. none of the statements A and B
.
For questions 6‐10, consider the following small database of four transactions. The minimum support is
60% and the minimum confidence is 80%.
Trans_id
Itemlist
T1
T2
T3
T4
{F, A, D, B}
{D, A, C, E, B}
{C, A, B, E}
{B, A, D}
6. The 1‐itemsets that satisfy the support criteria are:
A. {A}, {B}, {C}, {D}
B. {A}. {B}, {C}
C. {A}, {B}
D. None of the above
.
7. The 2‐itemsets that satisfy the support criteria are:
A. {BC}, {BE}, {CE}, {AE}
B. {AB}. {BD}, {AD}
C. {AE}, {BC}
D. {BC}
8. The 3‐itemsets that satisfy the support criteria are:
A. {ABC}, {ABE}, {BCD}, {ACD}
B. {ABE}. {BCD}, {ACD}
C. {ABE}, {BCD}
D. {ABD}
9. Which of the following is NOT a valid association rule?
A. A ‐> B
B. B ‐> A
C. A ‐> D
D. D ‐> A
10. Which of the following is NOT a valid association rule?
A. A ‐> DB
B. D ‐> AB
C. AD ‐> B
D. DB ‐> A
Data Mining: Assignment Week 3: Decision Trees
1. Internal nodes of a decision tree correspond to :( 1 Mark)
A. Attributes
B. Classes
C. Data instances
D. None of the above
Ans: A
Explanation: Each internal node of the tree corresponds to an attribute, and each leaf node corresponds to
a class label.
2. In a multiclass classification problem, Bayes classifier assigns an instance to the class
corresponding to: (1 mark)
A. Highest aposteriori probability
B. Highest apriori probability
C. Lowest aposteriori probability
D. Lowest apriori probability
Ans: A
Explanation: Bayes classifier is also known as MAP (Maximum Aposteriori Classifier.)
3. Three identical bags contain blue and yellow balls. The first bag contains 3 blue and 2 yellow
balls, the second bag has 4 blue and 5 yellow balls, and the third bag has 2 blue and 4 yellow balls.
A bag is chosen randomly and a ball is chosen from it. If the ball that is drawn out is blue, what will
be the probability that the second bag is chosen? (2 Marks)
A. 15/62
B. 27/62
C. 10/31
D. None of the above
Ans: C
Explanation: Apply Bayes theorem
P(Ball=Blue|II) = P(Ball=Blue|II)*P(II)/( P(Ball=Blue|I)*P(I)+ P(Ball=Blue|II)*P(II)+
P(Ball=Blue|III)*P(III))
For questions 4-9, consider the following table depicting whether a customer will buy a laptop or not.
SNo.
Age
Income
Student
Credit_rating
Buys_Computer
1
<=30
High
No
Fair
No
2
<=30
High
No
Excellent
No
3
31-40
High
No
Fair
Yes
4
>40
Medium
No
Fair
Yes
5
>40
Low
Yes
Fair
Yes
6
>40
Low
Yes
Excellent
No
7
31-40
Low
Yes
Excellent
Yes
8
<=30
Medium
No
Fair
No
9
<=30
Low
Yes
Fair
Yes
10
>40
Medium
Yes
Fair
Yes
11
<=30
Medium
Yes
Excellent
Yes
12
31-40
Medium
No
Excellent
Yes
13
31-40
high
Yes
Fair
Yes
14
>40
Medium
No
Excellent
No
4. What is the entropy of the dataset?(1 Mark)
A. 0.50
B. 0.94
C. 1
D. 0
Ans: B
Explanation:Entropy(9,5) = -(5/14)log(5/14) – (9/14)log(9/14) = 0.94
5. Which attribute would information gain choose as the root of the tree? (1 Mark)
A. Age
B. Income
C. Student
D. Credit_rating
Ans:A
Explanation: From information gain criterion. The Age has the highest information gain.
6. Whether a person will buy if {Age=35, Student=No, Income=Low, Credit_rating = Fair}? (1 Mark)
A. Yes
B. No
C. The example can’t be classified
D. Both classes are equally likely
Ans:A
Explanation:Build the tree and obtain the classification.
7. What class does the person{Age=42, Student=No, Income=Medium, Credit_rating = Excellent}? (1 Mark)
A. Yes
B. No
C. The example can not be classified
D. Both classes are equally likely
Ans: B
Explanation:Build the tree and obtain the classification.
8. What class does the person {Age=25, Student=No, Income=Medium, Credit_rating = Fair}? (1 Mark)
A. Yes
B. No
C. The example can not be classified
D. Both classes are equally likely
Ans: B
Explanation: Build The Tree.
9. Which attribute would information gain choose for Age=31-40? (1 Mark)
A. Student
B. Income
C. Is a leaf node with value Yes.
D. Credit_rating
Ans:C
Explanation:Construct the tree.
Data Mining: Assignment Week 5: Support Vector Machine
1. Support vector machine is:
A. Maximum aprori classifier
B. Maximum margin classifier
C. Minimum apriori classifier
D. Minimum margin classifier
Answer: B
2. Support vectors in SVM are:
A. Outliers
B. Subset of testing data points
C. Subset of training data points
D. Random points in the data set
Answer: C
3. In a hard margin support vector machine:
A. No training instances lie inside the margin
B. All the training instances lie inside the margin
C. Only few training instances lie inside the margin
D. None of the above
Answer: A
4. The Lagrange multipliers corresponding to the support vectors have a value:
A. equal to zero
B. less than zero
C. greater than zero
D. can take on any value
Answer: C
5. The primal optimization problem solved to obtain the hard margin optimal
separating hyperplane is:
A. Minimize ½ WTW, such that yi(WTXi+b) ≥ 1 for all i
B. Maximize ½ WTW, such that yi(WTXi+b) ≥ 1 for all i
C. Minimize ½ WTW, such that yi(WTXi+b) ≤ 1 for all i
D. Maximize ½ WTW, such that yi(WTXi+b) ≤ 1 for all i
Answer: A
6. The dual optimization problem solved to obtain the hard margin optimal separating
hyperplane is:
A. Maximize ½ WTW, such that yi(WTXi+b) ≥ 1- αi for all i
B. Minimize ½ WTW - αi(yi(WTXi+b) -1), such that αi ≥ 0, for all i
C. Minimize ½ WTW - αi, such that yi(WTXi+b) ≤ 1 for all i
D. Maximize ½ WTW + αi , such that yi(WTXi+b) ≤ 1 for all i
Answer: B
7. We are designing a SVM , WTX+b=0, suppose Xj’s are the support vectors and αj’s
the corresponding Lagrange multipliers, then which of the following statements are
correct:
A. W = αjyjXj
B. αjyj = 0
C. Either A or B
D. Both A and B
Answer: D
8. If the hyperplaneWTX+b=0 correctly classifies all the training points (Xi, yi), where
yi={+1, -1}, then:
A. ||W-1|| = 2
B. X= 1
C. WTXi+b ≥ 0 for all i
D. yi(WTXi+b) ≥ 0 for all i
Answer: D
9. The dual optimization problem in SVM design is usually solved using:
A. Genetic programming
B. Neural programming
C. Dynamic programming
D. Quadratic programming
Answer: D
10. Slack variables are used in which of the below:
A. Soft margin SVM
B. Hard margin SVM
C. Both in Soft margin SVM and Hard margin SVM
D. Neither in Soft margin SVM nor in Hard margin SVM
Answer: A
Data Mining: Assignment Week 6: ANN
1. Sufficient Number of output nodes required in an ANN used for two-class
classification problem is:
A. Random number
B. Same as number of input nodes
C. 1
D. 2
Answer : c
2. How are the weights and biases initialized in an ANN in general?
A. Can be initialized randomly
B. Always initialized to zero
C. Always initialized to infinity
D. Always initialized as 1
Answer : A
3. In which of the below neural network, the links may connect nodes
within the same layer or nodes from one layer to the previous layers?
A. Perceptron
B. Feed-forward neural network
C. Recurrent neural network
D. Both B, C
Answer : C
4.Neural Networks are complex ______________ with many parameters.
A. Linear Functions
B. Nonlinear Functions
C. Discrete Functions
D. Exponential Functions
Ans : A
5. Artificial neural network used for:
A. Pattern Recognition
B. Classification
C. Clustering
D. All of the above
Ans: D
6. A neuron with 3 inputs has the weight vector [0.2 -0.1 0.1]^T and a bias θ = 0. If
the input vector is X = [0.2 0.4 0.2]^T then the total input to the neuron is:
A. 0.2
B. 0.02
C. 0.4
D. 0.10
Ans: B
7. A neural Network given below takes two binary inputs X1, X2 ϵ {0,1} and the
activation function for each neuron is the binary threshold function (g(a)= 1 if a >0; 0
otherwise). Which of the following logical functions does it compute?
A. AND
B. NAND
C. XOR
D. NOR
Ans: D
8. The neural network given bellow takes two binary valued inputs x 1, x 2 ϵ {0,1}, the
activation function for each neuron is the binary threshold function (g(a)= 1 if a >0; 0
otherwise). Which of the following logical functions does it compute?
A. AND
B. NAND
C. XOR
D. OR
Ans: C
9. The neural network given bellow takes two binary valued inputs x 1, x 2 ϵ {0,1} and
the activation function is the binary threshold function ( h ( z )=1 if z >0 ;0 otherwise ) . Which
of the following logical functions does it compute?
-1
3
X1
2
X2
A. OR
B. AND
C. NAND
D. NOR
Ans: B
2
10. Under which of the following situation would you expect overfitting to happen?
A. With training iterations error on training set as well as test set decreases
B. With training iterations error on training set decreases but test set
increases
C. With training iterations error on training set as well as test set increases
D. With training iterations training set as well as test set error remains constant
Ans: B
