DMW MCQ

Seat No -
Total number of questions : 60
12695_Data Mining and Warehousing

Time : 1hr
Max Marks : 50
N.B
1) All questions are Multiple Choice Questions having single correct option.
2) Attempt any 50 questions out of 60.
3) Use of calculator is allowed.
4) Each question carries 1 Mark.
5) Specially abled students are allowed 20 minutes extra for examination.
6) Do not use pencils to darken answer.
7) Use only black/blue ball point pen to darken the appropriate circle.
8) No change will be allowed once the answer is marked on OMR Sheet.
9) Rough work shall not be done on OMR sheet or on question paper.
10) Darken ONLY ONE CIRCLE for each answer.
Q.no 1. What does the leaf node in decision tree indicates
A : sub tree
B : class label
C : testing node
D : condition
Q.no 2. sensitivity is also known as
A : false rate
B : recall
C : negative rate
D : recognition rate
Q.no 3. the negative tuples that were correctly labeled by the
classifier
A : False positives(FP)
B : True positives(TP)
C : True negatives (TN)
D : False negatives(FN)
Q.no 4. Removing duplicate records is a process called
A : recovery
B : data cleaning
C : data cleansing
D : data pruning
Q.no 5. For Apriori algorithm, what is the first phase?
A : Pruning
B : Partitioning
C : Candidate generation
D : Itemset generation
Q.no 6. Multi-class classification makes the assumption that each sample is

assigned to
A : one and only one label
B : many labels
C : one or many labels
D : no label
Q.no 7. Multilevel association rules can be mined efficiently using
A : Support
B : Confidence
C : Support count
D : Concept Hierarchies under support-confidence framework
Q.no 8. What is the method to interpret the results after rule generation?
A : Absolute Mean
B : Lift ratio
C : Gini Index
D : Apriori
Q.no 9. Self-training is the simplest form of
A : supervised classification
B : semi-supervised classification
C : unsupervised classification
D : regression
Q.no 10. Which of the following is direct application of frequent itemset mining?
A : Social Network Analysis
B : Market Basket Analysis
C : Outlier Detection
D : Intrusion Detection
Q.no 11. Hidden knowledge referred to
A : A set of databases from different vendors, possibly using different database

paradigms
B : An approach to a problem that is not guaranteed to work but performs well in most
cases
C : Information that is hidden in a database and that cannot be recovered by a simple

SQL query
D : None of these
Q.no 12. The schema is collection of stars. Recognize the type of schema.
A : Star Schema
B : Snowflake schema
C : Fact constellation
D : Database schema
Q.no 13. The Synonym for data mining is
A : Data warehouse
B : Knowledge discovery in database
C : ETL
D : Business Intelligemce
Q.no 14. Which of the following are methods for supervised classification?
A : Decision tree
B : K-Means
C : Hierarchical
D : Apriori
Q.no 15. These are the intermediate servers that stand in between a relational
back-end server and client front-end tools
A : ROLAP
B : MOLAP
C : HOLAP
D : HaoLap
Q.no 16. Color is an example of which type of attribute
A : Nominal
B : Binary
C : Ordinal
D : numeric
Q.no 17. What are two steps of tree pruning work?
A : Pessimistic pruning and Optimistic pruning
B : Postpruning and Prepruning

C : Cost complexity pruning and time complexity pruning
D : None of the options
Q.no 18. A data cube is defined by
A : Dimensions
B : Facts
C : Dimensions and Facts
D : Dimensions or Facts
Q.no 19. For Apriori algorithm, what is the second phase?
A : Pruning
B : Partitioning
Q.no 20. What is the range of the cosine similarity of the two documents?
A : Zero to One
B : Zero to infinity
C : Infinity to infinity
D : Zero to Zero
Q.no 21. Lazy learner classification approach is
A : learner waits until the last minute before constructing model to classify
B : a given training data constructs a model first and then uses it to classify
C : the network is constructed by human experts
Q.no 22. Cross validation involves
A : testing the machine on all possible ways by substituting the original sample into
training set
B : testing the machine on all possible ways by dividing the original sample into
training and validation sets.
C : testing the machine with only validation sets
D : testing the machine on only testing datasets.
Q.no 23. The rule is considered as intersting if
A : They satisfy both minimum support and minimum confidence threshold
B : They satisfy both maximum support and maximum confidence threshold
C : They satisfy maximum support and minimum confidence threshold
D : They satisfy minimum support and maximum confidence threshold
Q.no 24. Data independence means
A : Data is defined separately and not included in programs
B : Programs are not dependent on the physical attributes of the data
C : Programs are not dependent on the logiical attributes of the data
D : Programs are not dependent on the physical attributes as well as logical attributes
of the data
Q.no 25. Which of the following is a predictive model?
A : Clustering
B : Regression
C : Summarization
D : Association rules
Q.no 26. The data cubes are generally
A : 1 Dimensional
B : 2 Dimensional
C : 3 Dimensional
D : n-Dimensional
Q.no 27. Identify the example of sequence data

A : weather forecast
B : data matrix
C : market basket data
D : genomic data
Q.no 28. The frequent-item-header-table consists of number fields
A : Only one
B : Two
C : Three
D : Four
Q.no 29. How are metarules useful in mining of association rules?
A : Allow users to specify threshold measures
B : Allow users to specify task relevant data
C : Allow users to specify the syntactic forms of rules
D : Allow users to specify correlation or association
Q.no 30. Which of the following activities is a data mining task?
A : Monitoring the heart rate of a patient for abnormalities
B : Extracting the frequencies of a sound wave
C : Predicting the outcomes of tossing a (fair) pair of dice
D : Dividing the customers of a company according to their profitability
Q.no 31. When do you consider an association rule interesting?
A : If it only satisfies minimum support
B : If it only satisfies minimum confidence
C : If it satisfies both minimum support and minimum confidence
D : There are other measures to check interesting rules
Q.no 32. What is the approach of basic algorithm for decision tree induction?
A : Greedy
B : Top Down
C : Procedural
D : Step by Step
Q.no 33. What do you mean by support(A)?
A : Total number of transactions containing A
B : Total Number of transactions not containing A
C : Number of transactions containing A / Total number of transactions
D : Number of transactions not containing A / Total number of transactions
Q.no 34. Which of the following probabilities are used in the Bayes theorem.
A : P(Ci|X)
B : P(Ci)
C : P(X|Ci)
D : P(X)
Q.no 35. In which step of Knowledge Discovery, multiple data sources are
combined?
A : Data Cleaning
B : Data Integration
C : Data Selection
D : Data Transformation
Q.no 36. The Galaxy Schema is also called as
A : Star Schema
D : Database schema
Q.no 37. Handwritten digit recognition classifying an image of a handwritten
number into a digit from 0 to 9 is example of
A : Multiclassification
B : Multi-label classification
C : Imbalanced classification
D : Binary Classification
Q.no 38. What type of data do you need for a chi-square test?
A : Categorical
B : Ordinal
C : Interval
D : Scales
Q.no 39. For a classification problem with highly imbalanced class. The majority
class is observed 99% of times in the training data.
Your model has 99% accuracy after taking the predictions on test data. Which of
the following is not true in such a case?
A : Imbalaced problems should not be measured using Accuracy metric.
B : Accuracy metric is not a good idea for imbalanced class problems.
C : Precision and recall metrics aren’t good for imbalanced class problems.
D : Precision and recall metrics are good for imbalanced class problems.
Q.no 40. Which of the following property typically does not hold for similarity
measures between two objects ?
A : Symmetry
B : Definiteness
C : Triangle inequality
D : Transitive
Q.no 41. Cost complexity pruning algorithm is used in?
A : CART
B : C4.5
C : ID3
D : ALL
Q.no 42. In one of the frequent itemset example, it is observed that if tea and milk
are bought then sugar is also purchased by customers. After, generating an
association rule among the given set of items, it is inferred:
A : {Tea} is antecedent and {sugar} is consequent
B : {Tea} is antecedent and the itemset {milk, sugar} is consequent
C : The itemset {Tea, milk} is consequent and {sugar} is antecedent
D : The itemset { Tea, milk} is antecedent and {sugar} is consequent
Q.no 43. When do we use Manhattan distance in data mining?
A : Dimension of the data decreases
B : Dimension of the data increases
C : Underfitting
D : Moderate size of the dimensions
Q.no 44. Ordinal attribute has three distinct values such as Fair, Good, and
Excellent.
If x and y are two objects of ordinal attribute with Fair and Good values
respectively, then what is the distance from object y to x?
A:1
B:0
C : 0.5
D : 0.75
Q.no 45. Which of the following operation is requird to calculate cosine

similarity?
A : Vector dot product
B : Exponent
C : Modulus
D : Percentage
Q.no 46. Which is the most well known association rule algorithm and is used in
most commercial products.
A : Apriori algorithm
B : Pincer-search algorithm
C : Distributed algorithm
D : Partition algorithm
Q.no 47. What is the another name of Supremum distance?
A : Wighted Euclidean distance
B : City Block
distance
C : Chebyshev distance
D : Euclidean distance
Q.no 48. a model predicts 50 examples belonging to the minority class, 45 of which
are true positives and five of which are false positives. Precision of model is
A : Precision= 0.90
B : Precision= 0.79
C : Precision= 0.45
D : Precision= 0.68
Q.no 49. How the bayesian network can be used to answer any query?
A : Full distribution
B : Joint distribution
C : Partial distribution
D : All of the mentioned
Q.no 50. A sub-database which consists of set of prefix paths in the FP-tree co-
occuring with the sufix pattern is called as
A : Suffix path
B : FP-tree
C : Prefix path
D : Condition pattern base
Q.no 51. Which of the following sentence is FALSE regarding regression?
A : It relates inputs to outputs.
B : It is used for prediction.
C : It may be used for interpretation.
D : It discovers causal relationships.
Q.no 52. The basic idea of the apriori algorithm is to generate the item sets of a
particular size & scans the database. These item sets are
A : Primary
B : Secondary
C : Superkey
D : Candidate
Q.no 53. Which operation data warehouse requires ?
A : Initial loading of data
B : Transaction processing
C : Recovery
D : Concurrency control mechanisms
Q.no 54. The problem of finding hidden structure from unlabeled data is called as
A : Supervised learning
B : Unsupervised learning
C : Reinforcement Learning
D : Semisupervised learning
Q.no 55. A model makes predictions and predicts 120 examples as belonging to the
minority class, 90 of which are correct, and 30 of which are incorrect. Precision of
model is
A : Precision = 0.89
B : Precision = 0.23
C : Precision = 0.45
D : Precision = 0.75
Q.no 56. Accuracy is
A : Number of correct predictions out of total no. of predictions
B : Number of incorrect predictions out of total no. of predictions
C : Number of predictions out of total no. of predictions
D : Total number of predictions
Q.no 57. What does a Pearson's product-moment allow you to identify?
A : Whether there is a relationship between variables
B : Whether there is a significant effect and interaction of independent variables
C : Whether there is a significant difference between variables
D : Whether there is a significant effect and interaction of dependent variables
Q.no 58. A model makes predictions and predicts 90 of the positive class
predictions correctly and 10 incorrectly.Recall of model is
A : Recall=0.9
B : Recall=0.39
C : Recall=0.65
D : Recall=5.0
Q.no 59. Rotating the axes in a 3-D cube is the examplele of
A : Pivot
B : Roll up
C : Drill down
D : Slice
Q.no 60. These server performs the faster computation
A : ROLAP
B : MOLAP
C : HOLAP
D : HaoLap
Answer for Question No 1. is b
Answer for Question No 3. is c
Answer for Question No 6. is a
Answer for Question No 7. is d




Seat No -

Time : 1hr
Max Marks : 50
N.B
Q.no 1. Postpruning is
A : Removing branches from fully grown tree
B : Stop constructing tree if this would result in the measure falling below a threshold
C : construting a new tree
D : Flow-Chart
Q.no 2. If two documents are similar, then what is the measure of angle between
two documents?
A : 30
B : 60
C : 90
D:0
Q.no 3. CART stands for
A : Regression
B : Classification
C : Classification and Regression Trees
D : Decision Trees
Q.no 4. The first steps involved in the knowledge discovery is?
A : Data Integration
B : Data Selection
C : Data Transformation
D : Data Cleaning
A : ROLAP
B : MOLAP
C : HOLAP
D : HaoLap
A : false rate
B : recall
C : negative rate
Q.no 7. Which of the following is not a type of constraints?
A : Data constraints
B : Rule constraints
C : Knowledge type constraints
D : Time constraints
Q.no 8. Baysian classification in based on
A : probability for the hypothesis
B : Support
C : tree induction
D : Trees
Q.no 9. Which one of the following is true for decision tree
A : Decision tree is useful in decision making
B : Decision tree is similar to OLTP
C : Decision Tree is similar to cluster analysis
D : Decision tree needs to find probabilities of hypothesis

paradigms
cases

SQL query
D : None of these
Q.no 11. What is an alternative form of Euclidean distance?
A : L1 norm
B : L2 norm
C : Lmax norm
D : L norm
Q.no 12. The distance between two points calculated using Pythagoras theorem is
A : Supremum distance
B : Euclidean distance
C : Linear distance
D : Manhattan Distance
Q.no 13. What are closed frequent itemsets?
A : A closed itemset
B : A frequent itemset
C : An itemset which is both closed and frequent
D : Not frequent itemset
Q.no 14. A decision tree is also known as
A : general tree
B : binary tree
C : prediction tree
Q.no 15. cross-validation and bootstrap methods are common techniques for
assessing
A : accuracy
B : Precision
C : recall
D : performance
Q.no 16. A multidimensional data model is typically organized around a central

theme which is represented by
A : Dimension table
B : Fact table
C : Dimension table and Fact table
D : Dimension table or Fact table
Q.no 17. The problem of agents to learn from the environment by their
interactions with dynamic environment is done in
A : Reinforcement learning
C : Binary Classification
D : Multiclassification
Q.no 18. Entropy is a measure of
A : impurity of an attribute
B : Purity of an attribute
C : Weight of an attribute
D : Class of an attribute
classifier
Q.no 20. An ROC curve for a given

model shows the trade-off between
A : random sampling
B : test data and train data
C : cross validation
D : the true positive rate (TPR) and the false positive rate
(FPR)
Q.no 21. What is another name of data matrix?
A : Single mode
B : Two mode
C : Multi mode
D : Large mode
A : Clustering
B : Regression
C : Summarization
Q.no 24. Data independence means
A : Data is defined separately and not included in programs
B : Programs are not dependent on the physical attributes of the data
C : Programs are not dependent on the logiical attributes of the data
D : Programs are not dependent on the physical attributes as well as logical attributes
of the data
Q.no 26. If first object X and Y coordinates are 3 and 5 respectively and second
object X and Y coordinates are 10 and 3 respectively, then what is Manhattan
disstance between these two objects?
A:8
B : 13
C:9
D : 10
Q.no 27. Number of records are comparatively more in

A : OLAP
B : OLTP
C : Same in OLAP and OLTP
D : Can not compare
Q.no 28. Which of the following operations are used to calculate proximity
measures for ordinal attribute?
A : Replacement and discretization
B : Replacement and characterizarion
C : Replacement and normalization
D : Normalization and discretization
Q.no 29. Which of the following is necessary operation to calculate dissimilarity

between ordinal attributes?
A : Replacement of ordinal categories
B : Correlation coefficient
C : Discretization
D : Randomization
Q.no 30. Multilevel association rule mining is
A : Association rules generated from candidate-generation method
B : Association rules generated from without candidate-generation method
C : Association rules generated from mining data at multiple abstarction level
D : Assocation rules generated from frequent itemsets
Q.no 31. In a decision tree each leaf node represents
A : Test conditions
B : Class labels
C : Attribute values
D : Decision
A : Star Schema
D : Database schema
Q.no 33. For mining frequent itemsets, the Data format used by Apriori and FP-
Growth algorithms are
A : Apriori uses horizontal and FP-Growth uses vertical data format
B : Apriori uses vertical and FP-Growth uses horizontal data format
C : Apriori and FP-Growth both uses vertical data format
D : Apriori and FP-Growth both uses horizontal data format
Q.no 34. The property of Apriori algorithm is
A : All nonempty subsets of a frequent itemsets must also be frequent
B : All empty subsets of a frequent itemsets must also be frequent
C : All nonempty subsets of a frequent itemsets must be not frequent
D : All nonempty subsets of a frequent itemsets can frequent or not frequent
Q.no 35. It is the main technique employed for data selection.
A : Noise
B : Sampling
C : Clustering
D : Histogram
Q.no 36. The probability of a hypothesis before the presentation of evidence is

called as
A : Apriori probability
B : subjective probability
C : posterior probability
D : conditional probability
combined?
A : Data Cleaning
C : Data Selection
Q.no 38. Some company wants to divide their customers into distinct groups to
send offers this is an example of
A : Data Extraction
B : Data Classification
C : Data Discrimination
D : Data Selection
Q.no 39. The accuracy of a classifier on a given test set is the percentage of
A : test set tuples that are correctly classified by the classifier
B : test set tuples that are incorrectly classified by the classifier
C : test set tuples that are incorrectly misclassified by the classifier
D : test set tuples that are not classified by the classifier
Q.no 40. Which of the following is measure of document similarity?
A : Cosine dissimilarity
B : Sine similarity
C : Sine dissimilarity
D : Cosine similarity
Q.no 41. Which one of these is a tree based learner?
A : Rule based
B : Bayesian Belief Network

C : Bayesian classifier
D : Random Forest
Q.no 43. Transforming a 3-D cube into a series of 2-D planes is the examplele of
A : Pivot
B : Roll up
C : Drill down
D : Slice
Q.no 44. What is the range of the angle between two term frequency vectors?
A : Zero to Thirty
B : Zero to Ninety
C : Zero to One Eighty
D : Zero to Fourty Five
Q.no 45. Name the property of objects for which distance from first object to
second and vice-versa is same.
A : Symmetry
B : Transitive
C : Positive definiteness
D : Traingle inequality
Excellent.
A:1
B:0
C : 0.5
D : 0.75
Q.no 47. A concept hierarchy that is a total or partial order among attributes in a
database schema is called
A : Mixed hierarchy
B : Total hierarchy
C : Schema hierarchy
D : Concept generalization
A : CART
B : C4.5
C : ID3
D : ALL
Q.no 50. A database has 4 transactions.Of these, 4 transactions include milk and
bread. Further , of the given 4 transactions, 3 transactions include cheese. Find
the support percentage for the following association rule, " If milk and bread
purchased then cheese is also purchased".
A : 0.6
B : 0.75
C : 0.8
D : 0.7
A : Precision= 0.90
B : Precision= 0.79
C : Precision= 0.45
D : Precision= 0.68
A : Suffix path
B : FP-tree
C : Prefix path
Q.no 53. High entropy means that the partitions in classification are
A : pure
B : Not pure
C : Useful
D : Not useful
Q.no 55. The following represents age distribution of students in an elementary

class. Find the mode of the values: 7, 9, 10, 13, 11, 7, 9, 19, 12, 11, 9, 7, 9, 10, 11.
A:7
B:9
C : 10
D : 11
Q.no 57. Correlation analysis is used for
A : handling missing values
B : identifying redundant attributes
C : handling different data formats
D : eliminating noise
Q.no 58. A data normalization technique for real-valued attributes that divides
each numerical value by the same power of 10.
A : min-max normalization
B : z-score normalization
C : decimal scaling
D : decimal smoothing
A : Pivot
B : Roll up
C : Drill down
D : Slice
Q.no 60. Holdout method, Cross-validation and Bootstrap methods are techniques
to estimate
A : Precision
B : Classifier performance
C : Recall
D : F-measure




Seat No -

Time : 1hr
Max Marks : 50
N.B
Q.no 1. Which angle is used to measure document similarity?
A : Sin
B : Tan
C : Cos
D : Sec
B : Data Selection
D : Data Cleaning
assessing
A : accuracy
B : Precision
C : recall
D : performance
Q.no 4. The task of building decision model from labeled training data is called as
A : Supervised Learning
B : Unsupervised Learning
D : Structure Learning

A : Dimension table
B : Fact table
Q.no 6. How can one represent document to calculate cosine similarity?
A : Vector
B : Matirx
C : List
D : Term frequency vector
Q.no 7. What is association rule mining?
A : Using association to find correlation rules
B : Same as frequent itemset mining
C : Finding of strong association rules using frequent itemsets

D : Finding of frequent itemset from large database
Q.no 8. What do you mean by dissimilarity measure of two objects?
A : Is a numerical measure of how alike two data objects are.
B : Is a numerical measure of how different two data objects are.
C : Higher when objects are more alike
D : Lower when objects are more different
A : Regression
B : Classification
D : Decision Trees
Q.no 10. OLAP database design is
A : Application-oriented
B : Object-oriented
C : Goal-oriented
D : Subject-oriented
A : Absolute Mean
B : Lift ratio
C : Gini Index
D : Apriori
C : Linear distance
A : Zero to One
D : Zero to Zero
A : Nominal
B : Binary
C : Ordinal
D : numeric
A : Star Schema
D : Database schema
Q.no 16. Data used to build a data mining model.
A : Validation Data
B : Training Data
C : Testing Data
D : Hidden Data
Q.no 18. accuracy is used to measure
A : classifier’s true abilities
B : classifier’s analytic abilities
C : classifier’s decision abilities
D : classifier’s predictive abilities
Q.no 19. recall is a measure of
A : completeness of what percentage

of positive tuples are labeled
B : a measure of exactness for misclassification
C : a measure of exactness of what percentage of tuples are not classified
D : a measure of exactness of what percentage of tuples labeled as

negative are at actual
Q.no 20. Learning algorithm which trains with combination of labeled and
unlabeled data.
A : Supervised
B : Unsupervised
C : Semi supervised
D : Non- supervised
Q.no 21. What is uniform support in multilevel association rule minig?
A : Use of minimum support
B : Use of minimum support and confidence
C : Use of same minimum threshold at each abstraction level
D : Use of minimum support and support count

Q.no 23. Which of the following operation is correct about supremum distance?
A : It gives maximum difference between any attribute of the objects
B : It gives minimum difference between any attribute of the objects
C : It gives maximum difference between fisrt attribute of the objects
D : It gives minimum difference between fisrt attribute of the objects
Q.no 24. Frequent patterns generated from association can be used for
classification is called
A : Naïve Bays
B : Associative Classification
C : Preditctive Mining
D : Decision Tree
Q.no 25. Holdout and random subsampling are common techniques for assessing
A : K-Fold validation
B : cross validation
C : accuracy
D : sampling
Q.no 26. Which statement is true about the decision tree attribute selection
process
A : A categorical attribute may appear in a tree node several times but a numeric
attribute may appear at most once.
B : A numeric attribute may appear in several tree nodes but a categorical attribute
may appear at most once.
C : Both numeric and categorical attributes may appear in several tree nodes.
D : Numeric and categorical attributes may appear in at most one tree node.
Q.no 27. Which of the following is not correct use of cross validation?
A : Selecting variables to include in a model
B : Comparing predictors
C : Selecting parameters in prediction function
D : classification
Q.no 28. In asymmetric attribute
A : No value is considered important over other values
B : All values are equal
C : Only non-zero value is important
D : Range of values is important
Q.no 29. When do you consider an association rule interesting?
A : If it only satisfies minimum support
B : If it only satisfies minimum confidence
C : If it satisfies both minimum support and minimum confidence
D : There are other measures to check interesting rules
Q.no 30. How will you counter over-fitting in decision tree?
A : By creating new rules
B : By pruning the longer rules
C : Both By pruning the longer rules’ and ‘ By creating new rules’
D : BY creating new tree
A : Noise
B : Sampling
C : Clustering
D : Histogram
Q.no 32. If A, B are two sets of items, and A is a subset of B. Which of the following
statement is always true?
A : Support(A) is less than or equal to Support(B)
B : Support(A) is greater than or equal to Support(B)
C : Support(A) is equal to Support(B)
D : Support(A) is not equal to Support(B)
Q.no 33. Which is the wrong combination.
A : True negative=correctly indentified
B : False negative=incorrectly identified
C : False positive=correctly identified
D : True positive=correctly identified
Q.no 34. The data cubes are generally
A : 1 Dimensional
B : 2 Dimensional
C : 3 Dimensional
D : n-Dimensional
Q.no 35. A nearest neighbor approach is best used
A : with large-sized datasets.
B : when irrelevant attributes have been removed from the data.
C : when a generalized model of the data is desireable.
D : when an explanation of what has been found is of primary importance.
Q.no 36. The confusion matrix is a useful tool for analyzing
A : Regression
B : Classification
C : Sampling
D : Cross validation

A : Categorical
B : Ordinal
C : Interval
D : Scales
Q.no 39. Sensitivity is also referred to as
A : misclassification rate
B : true negative rate
C : True positive rate
D : correctness
Q.no 40. Number of records are comparatively more in
A : OLAP
B : OLTP
C : Same in OLAP and OLTP
D : Can not compare
Q.no 42. Which operation is required to calculate Hamming distacne between two
objects?
A : AND
B : OR
C : NOT
D : XOR
Q.no 43. This technique uses mean and standard deviation scores to transform
real-valued attributes.
A : decimal scaling
B : min-max normalization
C : z-score normalization
D : logarithmic normalization
Q.no 44. Consider three itemsets V1={tomato, potato,onion}, V2={tomato,potato},

V3={tomato}. Which of the following statement is correct?
A : support(V1) is greater than support (V2)
B : support(V3) is greater than support (V2)
C : support(V1) is greater than support(V3)
D : support(V2) is greater than support(V3)
A : Rule based
D : Random Forest
C : Underfitting

Q.no 47. The cuboid that holds the lowest level of summarization is called as
A : 0-D cuboid
B : 1-D cuboid
C : Base cuboid
D : 2-D cuboid
Q.no 48. In Binning, we first sort data and partition into (equal-frequency) bins
and then which of the following is not valid step
A : smooth by bin boundaries
B : smooth by bin median
C : smooth by bin means
D : smooth by bin values
A : Recall=0.9
B : Recall=0.39
C : Recall=0.65
D : Recall=5.0
A : 0.6
B : 0.75
C : 0.8
D : 0.7
A : Primary
B : Secondary
C : Superkey
D : Candidate
A : Symmetry
B : Transitive
Q.no 55. These numbers are taken from the number of people that attended a
particular church every Friday for 7 weeks: 62, 18, 39, 13, 16, 37, 25. Find the
mean.
A : 25
B : 210
C : 62
D : 30

A:7
B:9
C : 10
D : 11
Q.no 60. The tables are easy to maintain and saves storage space.
A : Star Schema
D : Database schema




Seat No -

Time : 1hr
Max Marks : 50
N.B
A : Vector
B : Matirx
C : List
Q.no 2. In Data Characterization, class under study is called as?
A : Study Class
B : Intial Class
C : Target Class
D : Final Class


classifier
Q.no 5. A person trained to interact with a human expert in order to capture their
knowledge.
A : knowledge programmer
B : knowledge developer
C : knowledge engineer
D : knowledge extractor
A : recovery
B : data cleaning
C : data cleansing
D : data pruning
D : regression
A : Zero to One
D : Zero to Zero


Q.no 10. The task of building decision model from labeled training data is called
as
B : Data Selection
D : Data Cleaning
A : false rate
B : recall
C : negative rate
A : general tree
B : binary tree
C : prediction tree
Q.no 14. Supervised learning and unsupervised clustering both require at least
one
A : hidden attribute
B : output attribute
C : input attribute
D : categorical attribute
C : Linear distance
A : Sin
B : Tan
C : Cos
D : Sec

paradigms
cases
SQL query
D : None of these
Q.no 18. The example of knowledge type constraints in constraint based mining is
A : Association or Correlation
B : Rule templates
C : Task relevant data
D : Threshold measures
Q.no 19. Which technique finds the frequent itemsets in just two database scans?
A : Partitioning
B : Sampling
C : Hashing
D : Dynamic itemset counting
Q.no 20. A data matrix in which attributes are of the same type and asymmetric is
called
A : Pattern matrix
B : Sparse data matrix
C : Document term matrix
D : Normal matrix
Q.no 21. Specificity is also referred to as
A : true negative rate
B : correctness
C : misclassification rate
D : True positive rate
A:8
B : 13
C:9
D : 10
Q.no 23. Which of the following property typically does not hold for similarity
measures between two objects ?
A : Symmetry
B : Definiteness
C : Triangle inequality
D : Transitive
Q.no 25. One of the most well known software used for classification is
A : Java
B : C4.5
C : Oracle
D : C++
Q.no 26. This supervised learning technique can process both numeric and
categorical input attributes.
A : linear regression
B : Bayes classifier
C : logistic regression
D : backpropagation learning
Q.no 27. A lattice of cuboids is called as
A : Data cube
B : Dimesnion lattice
C : Master lattice
D : Fact table
Q.no 28. K-fold Cross Validation envisages
A : partitioning of the original sample into one sample.
B : partitioning of the original sample into ‘k’ equal sized sub-samples.
C : partitioning of the original sample into ‘k’ unequal sized sub-samples.
D : partitioning of the original sample into ‘k’ random samples.
Q.no 29. The fact table contains
A : The names of the facts
B : Keys to each of the related dimension tables
C : Facts and keys
D : Facts or keys
Q.no 31. Which of the following operation is correct about supremum distance?
A : It gives maximum difference between any attribute of the objects
B : It gives minimum difference between any attribute of the objects
C : It gives maximum difference between fisrt attribute of the objects
D : It gives minimum difference between fisrt attribute of the objects

Q.no 32. What type of matrix is required to represent binary data for proximity
measures?
A : Normal matrix
B : Sparse matrix
C : Dense matrix
D : Contingency matrix
D : correctness
Q.no 34. What is the limitation behind rule generation in Apriori algorithm?
A : Need to generate a huge number of candidate sets
B : Need to repeatedly scan the whole database and Check a large set of candidates by
pattern matching
C : Dropping itemsets with valued information
D : Both (a) dnd (b)
Q.no 36. Which of the following sequence is used to calculate proximity measures
for ordinal attribute?
A : Replacement discretization and distance measure
B : Replacement characterizarion and distance measure

C : Normalization discretization and distance measure
D : Replacement normalization and distance measure
A : Data Extraction
D : Data Selection
Q.no 39. This operation may add new dimension to the cube
A : Roll up
B : Drill down
C : Slice
D : Dice
A : Single mode
B : Two mode
C : Multi mode
D : Large mode
to estimate
A : Precision
C : Recall
D : F-measure
A : Pivot
B : Roll up
C : Drill down
D : Slice
A : Star Schema
D : Database schema
A : Pivot
B : Roll up
C : Drill down
D : Slice

A:7
B:9
C : 10
D : 11

A : decimal scaling
Q.no 49. These server performs the faster computation
A : ROLAP
B : MOLAP
C : HOLAP
D : HaoLap
A : CART
B : C4.5
C : ID3
D : ALL
A : pure
B : Not pure
C : Useful
D : Not useful
A : 0.6
B : 0.75
C : 0.8
D : 0.7
A : Suffix path
B : FP-tree
C : Prefix path
A : Primary
B : Secondary
C : Superkey
D : Candidate
A : Precision= 0.90
B : Precision= 0.79
C : Precision= 0.45
D : Precision= 0.68

objects?
A : AND
B : OR
C : NOT
D : XOR
A : Mixed hierarchy
B : Total hierarchy





Seat No -

Time : 1hr
Max Marks : 50
N.B

Q.no 2. Baysian classification in based on
A : probability for the hypothesis
B : Support
C : tree induction
D : Trees
Q.no 3. Which of the following is correct about Proximity measures?
A : Similarity
B : Dissimilarity
C : Similarity as well as Dissimilarity
D : Neither similarity nor dissimilarity
A : Pruning
B : Partitioning

unlabeled data.
A : Supervised
B : Unsupervised
C : Semi supervised
D : Non- supervised
Q.no 6. The most widely used metrics and tools to assess a classification model
are:
A : Conusion Matrix
B : Support
C : Entropy
D : Probability
A : Star Schema
D : Database schema

A : random sampling
(FPR)
A : Support
B : Confidence
C : Support count
Q.no 11. Data matrix is also called as
A : Object by object structure
B : Object by attribute structure
C : Attribute by attribute structure
D : Attribute by object structure
Q.no 12. Each dimension is represented by only one table. Recognize the type of
schema.
A : Star Schema
D : Database schema
A : Vector
B : Matirx
C : List
A : Absolute Mean
B : Lift ratio
C : Gini Index
D : Apriori
A : Regression
B : Classification
D : Decision Trees
A : false rate
B : recall
C : negative rate
Q.no 17. Height is an example of which type of attribute
A : Nominal
B : Binary
C : Ordinal
D : Numeric
assessing
A : accuracy
B : Precision
C : recall
D : performance


B : Object-oriented
C : Goal-oriented
Q.no 21. Every key structure in the data warehouse contains a time element
A : records
B : Explicitly
C : Implicitly and explicitly
D : Implicitly or explicitly
Q.no 22. This supervised learning technique can process both numeric and
categorical input attributes.
A : linear regression
B : Bayes classifier
C : logistic regression
D : backpropagation learning
Q.no 25. A frequent pattern tree is a tree structure consisting of
A : A frequent-item-node
B : An item-prefix-tree
C : A frequent-item-header table
D : both B and C
Q.no 26. Learning with a complete system in mind with reference to interactions
among
the systems and subsystems with proper understanding of systemic boundaries is
A : Multi-label classification
B : Reinforcement learning
C : Systemic learning
D : Machine Learning
A : Only one
B : Two
C : Three
D : Four
pattern matching

A : Single mode
B : Two mode
C : Multi mode
D : Large mode
A : Test conditions
B : Class labels
D : Decision
A : Data cube
C : Master lattice
D : Fact table
A:8
B : 13
C:9
D : 10
Q.no 37. one-versus-one(OVO) and one-versus-all (OVA) classification involves
A : more than two classes
B : Only two classes
C : Only one class
D : No class
Q.no 38. K-fold Cross Validation envisages
A : partitioning of the original sample into one sample.
B : partitioning of the original sample into ‘k’ equal sized sub-samples.
C : partitioning of the original sample into ‘k’ unequal sized sub-samples.
D : partitioning of the original sample into ‘k’ random samples.
A : Java
B : C4.5
C : Oracle
D : C++
A : Primary
B : Secondary
C : Superkey
D : Candidate
A : Rule based
D : Random Forest
Q.no 44. Which of the following operation is requird to calculate cosine

similarity?
A : Vector dot product
B : Exponent
C : Modulus
D : Percentage
A : CART
B : C4.5
C : ID3
D : ALL
A : Pivot
B : Roll up
C : Drill down
D : Slice
A : Zero to Thirty
B : Zero to Ninety
Q.no 50. If True Positives (TP): 7, False Positives (FP): 1,False Negatives (FN): 4,
True Negatives (TN): 18. Calculate Precision and Recall.
A : Precision = 0.88, Recall=0.64
B : Precision = 0.44, Recall=0.78
C : Precision = 0.88, Recall=0.22
D : Precision = 0.77, Recall=0.55
A : 0-D cuboid
B : 1-D cuboid
C : Base cuboid
D : 2-D cuboid
A : Recall=0.9
B : Recall=0.39
C : Recall=0.65
D : Recall=5.0
A : Symmetry
B : Transitive

C : Underfitting
objects?
A : AND
B : OR
C : NOT
D : XOR
A : Star Schema
D : Database schema
A : Precision= 0.90
B : Precision= 0.79
C : Precision= 0.45
D : Precision= 0.68
Q.no 60. Effectiveness of the browsing is highest. Recognize the type of schema.
A : Star Schema
D : Database schema




Seat No -

Time : 1hr
Max Marks : 50
N.B
A : Sin
B : Tan
C : Cos
D : Sec
Q.no 2. Data mining is best described as the process of
A : identifying patterns in data
B : deducing relationships in data
C : representing data
D : simulating trends in data

A : ROLAP
B : MOLAP
C : HOLAP
D : HaoLap
Q.no 4. What does the leaf node in decision tree indicates
A : sub tree
B : class label
C : testing node
D : condition

A : Dimension table
B : Fact table
Q.no 6. Data used to build a data mining model.
A : Validation Data
B : Training Data
C : Testing Data
D : Hidden Data
A : Data warehouse
C : ETL
A : Nominal
B : Binary
C : Ordinal
D : numeric
Q.no 9. Cotraining is one form of
A : sampling
D : semi-supervised classification
Q.no 10. What is C4.5 is used to build
A : Decision tree
B : Regression Analysis
C : Induction
D : Association Rules
Q.no 11. Training process that generates tree is called as
A : Pruning
B : Rule generation
C : Induction
D : spliiting
unlabeled data.
A : Supervised
B : Unsupervised
C : Semi supervised
D : Non- supervised
Q.no 13. Which of the following is not frequent pattern?
A : Itemsets
B : Subsequences
C : Substructures
D : Associations
Q.no 14. What is an alternative form of Euclidean distance?
A : L1 norm
B : L2 norm
C : Lmax norm
D : L norm
A : Zero to One
D : Zero to Zero
A : false rate
B : recall
C : negative rate
Q.no 18. Which of the following are methods for supervised classification?
A : Decision tree
B : K-Means
C : Hierarchical
D : Apriori
A : Star Schema
D : Database schema
A : recovery
B : data cleaning
C : data cleansing
D : data pruning
A : Star Schema
D : Database schema
A : records
B : Explicitly

Q.no 23. If x and y are two objects of nominal attribute with COMP and IT values
respectively, then what is the similarity between these two objects?
A : Zero
B : Infinity
C : Two
D : One
A : Data cube
C : Master lattice
D : Fact table

D : classification
A : Only one
B : Two
C : Three
D : Four
Q.no 29. Which of these distributions is used for a testing hypothesis?
A : Normal Distribution
B : Chi-Squared Distribution
C : Gamma Distribution
D : Poisson Distribution
A : Greedy
B : Top Down
C : Procedural
D : Step by Step
Q.no 31. Joins will be needed to execute the query. Recognize the type of schema.
A : Star Schema
D : Database schema

A : Data Extraction
D : Data Selection
Q.no 34. Which statement is true about the KNN algorithm?
A : All attribute values must be categorical
B : The output attribute must be cateogrical.
C : Attribute values may be either categorical or numeric.
D : All attributes must be numeric.
Q.no 35. The correlation coefficient is used to determine:
A : A specific value of the y-variable given a specific value of the x-variable
B : A specific value of the x-variable given a specific value of the y-variable
C : The strength of the relationship between the x and y variables
D : None of these
A : Categorical
B : Ordinal
C : Interval
D : Scales
combined?
A : Data Cleaning
C : Data Selection
Q.no 38. Which of the following is measure of document similarity?
A : Cosine dissimilarity
B : Sine similarity
C : Sine dissimilarity
D : Cosine similarity
Q.no 40. In multilevel association rules, which strategy is employed
A : Top-down
B : Recursive
C : Bottom-up
D : Divide and conquer
Q.no 41. precision of model is 0.75 and recall is 0.43 then F-Score is
A : F-Score= 0.99
B : F-Score= 0.84
C : F-Score= 0.55
D : F-Score= 0.49

A : Suffix path
B : FP-tree
C : Prefix path
mean.
A : 25
B : 210
C : 62
D : 30
C : Underfitting
A : Primary
B : Secondary
C : Superkey
D : Candidate
A : Rule based
D : Random Forest
A : Precision= 0.90
B : Precision= 0.79
C : Precision= 0.45
D : Precision= 0.68
A : Symmetry
B : Transitive

A:7
B:9
C : 10
D : 11
to estimate
A : Precision
C : Recall
D : F-measure
Excellent.
A:1
B:0
C : 0.5
D : 0.75
A : CART
B : C4.5
C : ID3
D : ALL
A : 0-D cuboid
B : 1-D cuboid
C : Base cuboid
D : 2-D cuboid
A : Pivot
B : Roll up
C : Drill down
D : Slice
B : City Block
distance
objects?
A : AND
B : OR
C : NOT
D : XOR




Seat No -

Time : 1hr
Max Marks : 50
N.B
A : Data warehouse
C : ETL
B : Rule templates
two documents?
A : 30
B : 60
C : 90
D:0
are:
A : Conusion Matrix
B : Support
C : Entropy
D : Probability
C : Linear distance
A : Nominal
B : Binary
C : Ordinal
D : Numeric
A : Vector
B : Matirx
C : List
A : sampling
Q.no 9. Which is the keyword that distinguishes data warehouses from other data
repository systems ?
A : Subject-oriented
B : Object-oriented
C : Client server
D : Time-invariant
D : regression
Q.no 11. Which of the following is correct about Proximity measures?
A : Similarity
B : Dissimilarity
C : Similarity as well as Dissimilarity
D : Neither similarity nor dissimilarity
A : Pruning
B : Partitioning

paradigms
cases

SQL query
D : None of these
A : Nominal
B : Binary
C : Ordinal
D : numeric
A : Decision tree
C : Induction
Q.no 16. Choose the correct concept hierarchy.
A : city < street < state < country
B : street < city < state < country
C : street > city > state > country
D : street > city > country > state
unlabeled data.
A : Supervised
B : Unsupervised
C : Semi supervised
D : Non- supervised
Q.no 18. An automatic car driver and business intelligent systems are examples of
A : Regression
B : Classification
C : Machine Learning
D : Reinforcement learning
Q.no 19. Which of the following is direct application of frequent itemset mining?
A : Social Network Analysis
B : Market Basket Analysis
C : Outlier Detection
D : Intrusion Detection


Q.no 21. The Microsoft SQL Server 2000 is the example of
A : ROLAP
B : MOLAP
C : HOLAP
D : HaoLap

A : Noise
B : Sampling
C : Clustering
D : Histogram
Q.no 26. Where does the bayes rule used?
A : Solving queries
B : Increasing complexity
C : Decreasing complexity
D : Answering probabilistic query
A : Roll up
B : Drill down
C : Slice
D : Dice
Q.no 28. If x and y are two objects of nominal attribute with COMP and IT values
respectively, then what is the similarity between these two objects?
A : Zero
B : Infinity
C : Two
D : One
A : records
B : Explicitly
measures?
A : Normal matrix
B : Sparse matrix
C : Dense matrix
combined?
A : Data Cleaning
C : Data Selection
A : Test conditions
B : Class labels
D : Decision
Q.no 34. To improve the accuracy of multiclass classification we can use
A : cross validation
B : sampling
C : Error-detecting codes
D : Error-correcting codes
training set
Q.no 36. OLAP Summarization means
A : Consolidated
B : Primitive
C : Highly detailed
D : Recent data
B : data matrix
D : genomic data
Q.no 38. Which of the following is necessary operation to calculate dissimilarity

between ordinal attributes?
A : Replacement of ordinal categories
B : Correlation coefficient
C : Discretization
D : Randomization
A : P(Ci|X)
B : P(Ci)
C : P(X|Ci)
D : P(X)
Excellent.
A:1
B:0
C : 0.5
D : 0.75
A : Suffix path
B : FP-tree
C : Prefix path
mean.
A : 25
B : 210
C : 62
D : 30
A : decimal scaling
A : Pivot
B : Roll up
C : Drill down
D : Slice
A : 0.6
B : 0.75
C : 0.8
D : 0.7
A : Star Schema
D : Database schema
A : Primary
B : Secondary
C : Superkey
D : Candidate
A : Symmetry
B : Transitive
objects?
A : AND
B : OR
C : NOT
D : XOR
A : Zero to Thirty
B : Zero to Ninety
A : F-Score= 0.99
B : F-Score= 0.84
C : F-Score= 0.55
D : F-Score= 0.49
A : Star Schema
D : Database schema
B : City Block
distance
A : CART
B : C4.5
C : ID3
D : ALL
A : Mixed hierarchy
B : Total hierarchy

C : Underfitting





Seat No -

Time : 1hr
Max Marks : 50
N.B
B : Data Selection
D : Data Cleaning

A : Decision tree
C : Induction
Q.no 4. Which of the following is not frequent pattern?
A : Itemsets
B : Subsequences
C : Substructures
D : Associations
C : Linear distance
A : Dimensions
B : Facts

A : random sampling
(FPR)
Q.no 8. Which of the following is the data mining tool?
A : Borland C
B : Weka
C : Borland C++
D : Visual C
A : sampling
schema.
A : Star Schema
D : Database schema

A : Zero to One
D : Zero to Zero
Q.no 15. to evaluate a classifier’s quality we use
A : confusion matrix
B : error detection code
C : error correction code
D : classifier
Q.no 17. Supervised learning and unsupervised clustering both require at least
one
C : input attribute
A : Regression
B : Classification
D : Decision Trees
Q.no 19. What are closed frequent itemsets?
A : A closed itemset
B : A frequent itemset
C : An itemset which is both closed and frequent
D : Not frequent itemset
Q.no 20. In Data Characterization, class under study is called as?
A : Study Class
B : Intial Class
C : Target Class
D : Final Class
Q.no 21. A nearest neighbor approach is best used
A : with large-sized datasets.
B : when irrelevant attributes have been removed from the data.
C : when a generalized model of the data is desireable.
D : when an explanation of what has been found is of primary importance.
Q.no 22. Lazy learner classification approach is
A : learner waits until the last minute before constructing model to classify
B : a given training data constructs a model first and then uses it to classify
C : the network is constructed by human experts

A : P(Ci|X)
B : P(Ci)
C : P(X|Ci)
D : P(X)
D : both B and C
Q.no 25. Holdout and random subsampling are common techniques for assessing
A : K-Fold validation
B : cross validation
C : accuracy
D : sampling
B : correctness

B : sampling
pattern matching
C : Only one class
D : No class
A : Consolidated
B : Primitive
C : Highly detailed
D : Recent data
Q.no 32. When you use cross validation in machine learning, it means
A : you verify how accurate your model is on multiple and different subsets of data.
B : you verify how accurate your model is on same dataset.
C : you verify how accurate your model is on new dataset.
D : you verify how accurate your model on unknown dataset

A : Greedy
B : Top Down
C : Procedural
D : Step by Step
Q.no 34. Which of the following operations are used to calculate proximity
measures for ordinal attribute?
A : Replacement and discretization
B : Replacement and characterizarion
C : Replacement and normalization
D : Normalization and discretization
Q.no 35. In Apriori algorithm, for generating e. g. 5 itemsets, we use
A : Frequent 5 itemsets
B : Frequent 3 itemsets
C : Frequent 4 itemsets
D : Frequent 6 itemsets
A : Clustering
B : Regression
C : Summarization
A : Noise
B : Sampling
C : Clustering
D : Histogram
A : Data Extraction
D : Data Selection
A : Data cube
C : Master lattice
D : Fact table
A : 0.6
B : 0.75
C : 0.8
D : 0.7
A : Suffix path
B : FP-tree
C : Prefix path
A : 0-D cuboid
B : 1-D cuboid
C : Base cuboid
D : 2-D cuboid
C : Underfitting
A : Pivot
B : Roll up
C : Drill down
D : Slice
Q.no 46. Which operation data warehouse requires ?
A : Initial loading of data
B : Transaction processing
C : Recovery
D : Concurrency control mechanisms
mean.
A : 25
B : 210
C : 62
D : 30
A : Pivot
B : Roll up
C : Drill down
D : Slice
A : pure
B : Not pure
C : Useful
D : Not useful
model is
A : Star Schema
D : Database schema
A : F-Score= 0.99
B : F-Score= 0.84
C : F-Score= 0.55
D : F-Score= 0.49
A : Recall=0.9
B : Recall=0.39
C : Recall=0.65
D : Recall=5.0
A : Star Schema
D : Database schema

A : CART
B : C4.5
C : ID3
D : ALL
C : decimal scaling





Seat No -

Time : 1hr
Max Marks : 50
N.B
A : Pruning
B : Partitioning
Q.no 2. Which of these is not a frequent pattern mining algorithm?
A : Decision trees
B : Eclat
C : FP growth
D : Apriori


A : random sampling
(FPR)
two documents?
A : 30
B : 60
C : 90
D:0
Q.no 7. Supervised learning and unsupervised clustering both require at least one
C : input attribute
Q.no 8. The fact is also called as
A : Dimension
B : Key
C : Schema
D : Measure
are:
A : Conusion Matrix
B : Support
C : Entropy
D : Probability
Q.no 10. A person trained to interact with a human expert in order to capture
their knowledge.
A : knowledge programmer
B : knowledge developer
C : knowledge engineer
D : knowledge extractor
Q.no 11. Training process that generates tree is called as
A : Pruning
B : Rule generation
C : Induction
D : spliiting
A : Star Schema
D : Database schema
C : Linear distance
Q.no 14. to evaluate a classifier’s quality we use
A : confusion matrix
B : error detection code
C : error correction code
D : classifier
A : Pruning
B : Partitioning
B : Rule templates
A : Nominal
B : Binary
C : Ordinal
D : Numeric
A : Dimensions
B : Facts
Q.no 21. The Microsoft SQL Server 2000 is the example of
A : ROLAP
B : MOLAP
C : HOLAP
D : HaoLap

measures?
A : Normal matrix
B : Sparse matrix
C : Dense matrix
D : correctness
Q.no 27. In Apriori algorithm, for generating e. g. 5 itemsets, we use
A : Frequent 5 itemsets
B : Frequent 3 itemsets
C : Frequent 4 itemsets
D : Frequent 6 itemsets

A : Data cube
C : Master lattice
D : Fact table
B : correctness
B : sampling
A : Roll up
B : Drill down
C : Slice
D : Dice
A : Star Schema
D : Database schema
C : Only one class
D : No class
A : Consolidated
B : Primitive
C : Highly detailed
D : Recent data
D : both B and C
A : Regression
B : Classification
C : Sampling
training set
A : Rule based
D : Random Forest
Excellent.
A:1
B:0
C : 0.5
D : 0.75
A : Pivot
B : Roll up
C : Drill down
D : Slice

A:7
B:9
C : 10
D : 11
A : Star Schema
D : Database schema
A : Zero to Thirty
B : Zero to Ninety
A : Suffix path
B : FP-tree
C : Prefix path
A : Pivot
B : Roll up
C : Drill down
D : Slice
model is
A : 0-D cuboid
B : 1-D cuboid
C : Base cuboid
D : 2-D cuboid
C : decimal scaling
A : pure
B : Not pure
C : Useful
D : Not useful
A : decimal scaling
A : F-Score= 0.99
B : F-Score= 0.84
C : F-Score= 0.55
D : F-Score= 0.49
A : Primary
B : Secondary
C : Superkey
D : Candidate





Seat No -

Time : 1hr
Max Marks : 50
N.B
A : Absolute Mean
B : Lift ratio
C : Gini Index
D : Apriori
B : Object-oriented
C : Goal-oriented

A : Support
B : Confidence
C : Support count
Q.no 5. Supervised learning and unsupervised clustering both require at least one
C : input attribute
Q.no 6. The task of building decision model from labeled training data is called as
A : Zero to One
D : Zero to Zero
Q.no 8. Multi-class classification makes the assumption that each sample is

assigned to
A : one and only one label
B : many labels
C : one or many labels
D : no label
Q.no 9. Which of these is not a frequent pattern mining algorithm?
A : Decision trees
B : Eclat
C : FP growth
D : Apriori
B : Data Selection
D : Data Cleaning
C : Linear distance

A : random sampling
(FPR)
schema.
A : Star Schema
D : Database schema
A : Nominal
B : Binary
C : Ordinal
D : Numeric
A : Sin
B : Tan
C : Cos
D : Sec
Q.no 18. Which of the following is the data mining tool?
A : Borland C
B : Weka
C : Borland C++
D : Visual C
A : general tree
B : binary tree
C : prediction tree


A : Greedy
B : Top Down
C : Procedural
D : Step by Step

D : classification

Q.no 28. The fact table contains
A : The names of the facts
B : Keys to each of the related dimension tables
C : Facts and keys
D : Facts or keys
A : records
B : Explicitly
A : Regression
B : Classification
C : Sampling
pattern matching
A : Java
B : C4.5
C : Oracle
D : C++
B : data matrix
D : genomic data
measures?
A : Normal matrix
B : Sparse matrix
C : Dense matrix
A : Data Extraction
D : Data Selection
A : Roll up
B : Drill down
C : Slice
D : Dice

A:7
B:9
C : 10
D : 11
mean.
A : 25
B : 210
C : 62
D : 30
A : Star Schema
D : Database schema
A : 0-D cuboid
B : 1-D cuboid
C : Base cuboid
D : 2-D cuboid
A : Star Schema
D : Database schema
model is
A : 0.6
B : 0.75
C : 0.8
D : 0.7
A : Zero to Thirty
B : Zero to Ninety


B : City Block
distance
A : decimal scaling
C : Underfitting
A : Suffix path
B : FP-tree
C : Prefix path
A : CART
B : C4.5
C : ID3
D : ALL
objects?
A : AND
B : OR
C : NOT
D : XOR




UNIT SUB : 410244 (D) DMW
ONE
Sr. Questions a b c d Ans
No.
1 Which of the following applied on warehouse? write only read only both a & b none
B
2 Data can be store , retrive and updated in … SMTOP OLTP FTP OLAP
B
3 Data mining is Extraction of interesting (non-trivial, implicit,
previously unknown and potentially useful) information or patterns
TRUE FALSE
A
from data in large databases
4 Data in the real world is incomplete inconsitent noisy all
D
5 What are Measure of Data Quality Accuracy Completen Consistenc all
ess y
D
6 Data cleaning is fill in missing values, smooth noisy data, identify or
remove outliers, and resolve inconsistencies
TRUE FALSE
A
7 Data integration is Integration of multiple databases, data cubes, or
files
TRUE FALSE
A
8 Data transformation is Normalization and aggregation TRUE FALSE
A
9 Data reduction Obtains reduced representation in volume but
produces the same or similar analytical results
TRUE FALSE
A
10 Data discretization is Part of data reduction but with particular

importance, especially for numerical data
TRUE FALSE
A
11 Missing data may be due to equipment inconsisten certain
malfunction t with other data may
all
D
recorded not be
data and considered
thus important
deleted at the time
data not of entry
entered
due to
misunderst
anding
12 Incorrect attribute values may due to faulty data data entry data
collection problems transmissio
all
D
instruments n problems
13 data cleaning is not required for duplicate records TRUE FALSE

B
14 Binning method first sort data and partition into (equi-depth) bins TRUE FALSE
A
15 Data can be smoothed by fitting the data to a function, such as with
regression.
TRUE FALSE
A
16 Linear regression - involves finding the___________line to fit two
attributes (or variables)
best average worst
A
17 Data cleaning is fill in __________ values existing missing

B
18 Data integration is Integration of multiple databases, data cubes, or
files
TRUE FALSE
A
19 Data transformation is ________________and aggregation Normalizati Denormali
on zation
A
20 Data reduction Obtains reduced representation in volume but

produces the_________ or similar analytical results
same different
A
21 Data discretization is Part of data reduction but with particular

importance, especially for _____________data
Character numerical
B
22 Redundant data occur often when integration of multiple databases TRUE FALSE
A
23 The same attribute may have different names in different databases TRUE FALSE
A
24 Careful integration of the data from multiple sources may help
reduce/avoid redundancies and inconsistencies
TRUE FALSE
A
25 Correlation coefficient is also called Pearson’s product moment

coefficient
TRUE FALSE
A
26 Min-max normalization performs a linear transformation on the
original data.
TRUE FALSE
A
27 The values for an attribute, A, are normalized based on the mean and Min-max
standard deviation of A
z-score
normalizati normalizat
B
on ion
28 The values for an attribute, A, are normalized based on the mean and TRUE
standard deviation of A in z-score normalization
FALSE
A
29 z-score normalization is useful when the actual minimum and
maximum of attribute A are unknown
TRUE FALSE
A
30 Normalization by decimal scaling normalizes by moving the decimal TRUE

point of values of attribute A.
FALSE
A
31 Data reduction obtains a reduced representation of the data set that is TRUE
much smaller in volume but yet produces the same (or almost the
FALSE
A
same) analytical results
32 Run Length Encoding is lossless TRUE FALSE
A
33 Jpeg compression is lossy lossless
A
34 Wavelet Transform Decomposes a signal into different frequency
subbands
TRUE FALSE
A
35 Principal Component Analysis (PCA) is used for dimensionality
reduction
TRUE FALSE
A
36 Normalization by______________ scaling normalizes by moving the
decimal point of values of attribute A.
binary octal decimal
C
37 Data cube aggregation is normalization TRUE FALSE
B
38 ordinal attribute have values from an ___________set ordered unordered
A
39 Run Length Encoding is lossy lossless
B
40 Nominal attribute have values from an ___________set ordered unordered
B
TWO

No.
1 What is the type of relationship in star schema? many-to-man one-to-one
y.
many-to-one one-to-many
d
2 Fact tables are ___________. completely partially completely
demoralized. demoralized. normalized.
partially
normalized.
c
3 Data warehouse is volatile, because obsolete data are
discarded
TRUE FALSE
b
4 Which is NOT a basic conceptual schema in Data Modeling of Star schema
Data Warehouses?
Tree schema Snowflake
schema
Fact
constellations
b
5 Which is NOT a valid OLAP Rule by E.F.Codd? Accessibility Transparency Flexible

reporting
Reliability
d
6 Which is NOT a valid layer in Three-layer Data Warehouse

Architecture in Conceptual View?
Processed
data layer
Real-time
data layer
Derived data Reconciled
layer data layer
a
7 Among the types of fact tables which is not a correct type ? Fact-less fact
table
Transaction
fact tables
Integration
fact tables
Aggregate fact
tables
c
8 Among the followings which is not a characteristic of Data
Warehouse?
Integrated Volatile Time-variant Subject
oriented
b
9 what is not considered as isssues in data warehousing? optimization data
transformatio
extraction inter
mediation
d
n
10 which one is NOT considering as a standard query
technique?
Drill-up Drill-across DSS Pivoting
c
11 Among the following which is not a type of business data ? Real time data Application
data
Reconciled
data
Derived data
b
12 A data warehouse is which of the following? Can be
updated by
Contains
numerous
Organized
around
Contains only
current data.
c
end users. naming important
conventions subject areas.
and formats.
13 A snowflake schema is which of the following types of

tables?
Fact Dimension Helper All of the
above
d
14 The extract process is which of the following? Capturing all
of the data
Capturing a
subset of the
Capturing all
of the data
Capturing a
subset of the
b
contained in data contained in data
various contained in various contained in
operational various decision various
systems operational support decision
systems systems support
systems
15 The generic two-level data warehouse architecture includes
which of the following?
At least one
data mart
Data that can Near
extracted real-time
All of the
above.
b
from updates
numerous
internal and
external
sources
16 Which one is correct regarding MOLAP ? A.Data is
stored and fetched from the main data warehouse.
All are
incorrect
A and B is
correct.
Only C Only A
a
B.Use complex SQL queries to fetch data from the main
warehouse C.Large volume of data
is used.
17 In terms of data warehouse,metadata can be define as,
A.Metadata is a road-map to data warehouse B.Metadata in
A and B is
correct
A and C is
correct
B is correct All are
incorrect
d
data warehouse defines the warehouse objects.
C.Metadata acts as a directory.
18 In terms of RLOP model, choose the most suitable answer A and B is

A.The warehouse stores atomic data. B.The application layer correct
A and C is
correct
B & C is
correct
All are
incorrect
d
generates SQL for the two dimensional view. C.The
presentation layer provides the multidimensional view.
19 In the OLAP model, the _____________ provides the

multidimensional view.
C. Data layer D. Data link
layer
B.
Presentation
A. Application
layer
c
layer
20 Which of the following is not true regarding characteristics

of warehoused data?
Changed data Data
will be added warehouse
Obsolete data
are discarded
Users can
change data
d
as new data can contains once entered
historical data into the data
warehouse
21 ETL is an abbreviation for Elevation, Transformation and

Loading
TRUE FALSE
b
22 which is the core of the multidimensional model that consists Multidimensi Data model
of a large set of facts and a number of dimensions? onal cube
Data cube None of the
above
c
23 Which of the following statements is incorrect ROLAPs have Data form of
large data ROLAP is
MOLAP uses
sparse matrix
Access for
MOLAP is
b
volumes large technology to faster than
multidimenti manage data ROLAP
onal array sparcity
made of
cubes
24 Which of the following standard query techniques increase

the granularity
roll-up dril-down slicing dicing
b
25 The full form of OLAP is Online

Analytical
Online
Advanced
Online
Analytical
Online
Advanced
a
Processing Processing Performance Preparation
26 Which of the following statements is/are incorrect about

ROLAP A) ROLAP
A and B B and C A and C A
b
fetched data from datawarehouse. B) ROLAP data
store as data cubes. C) ROLAP use sparse
matrix to manage data sparsity.
27 ________ is a standard query technique that can be used
within OLAP to zoom in to more detailed data by changing
Drill-up Drill-down Pivoting Drill-across
b
dimensions.
28 Which of the following statements is/are correct about Fact

constellation schema A) Fact
A B A and C All of the
above
d
constellation schema can be seen as a combination of many
star schemas. B) It is possible to
cerate fact constellation schema, for each star schema or
snowflake schema. C) Can be identified as a
flexible schema for implementation.
29 How to describe the data contained in the data warehouse? Relational
data
Operational
data
Meta data Informationa
l data
c
30 The output of an OLAP query is displayed as a A.Pivot

B.Matrix C.Excel
A A,B B,C All of the
above
c
31 One can perform Query operations in the data present in

Data Warahouse
TRUE FALSE
a
32 A ____________ combines facts from multiple processes into a Aggregate fact Consolidated Transaction
single fact table and eases the analytic burden on BI table fact table fact table
Accumulating
snapshot fact
b
applications. table
33 In OLAP operations, Slicing is the technique of ______________ Selecting one

particular
Selecting two
or more
Rotating the
data axes in
Performing
aggregation
a
dimension dimensions order to on a data
from a given from a given provide an cube
cube and cube and alternative
providing a providing a presentation
new sub-cube new sub-cube of data
34 Standalone data marts built by drawing data directly from

operational or external sources of data or both are known as
TRUE FALSE
a
independent data marts
35 Focusing on the modeling and analysis of data for decision

makers, not on daily operations or transaction processing is
Integrated Time-variant Subject
oriented
Non-volatile
c
known as
36 Most of the time data ware house is
B Write
A Read A B A and B None of the
above
a
37 Data granularity is ------------------- of details of data ?

A.summarization B.transformation
A&B B&C A,B&C C
d
C.level
38 Which one is not a type of fact? Fully
Addictive
Cumulative
addictive
Semi
Addictive
Non Addictive
c
39 When the level of details of data is reducing the data

granularity goes higher
TRUE FALSE
b
40 Data Warehouses are having summarized and reconciled

data which can be used by decision makers
TRUE FALSE
a
41 _______ refers to the currency and lineage of data in a data

warehouse
Operational
metadata
Business
metadata
Technical
metadata
End-User
meatdata
a
THREE
Sr. No. Questions a b c d Ans
1 Euclidean distance measure is A stage of the KDD

process in which
The process of
finding a solution
The distance
between two points
None of these
c
new data is added for a problem as calculated using
to the existing simply by the Pythagoras
selection. enumerating all theorem
possible solutions
according to some
pre-defined order
and then testing
them
2 Hidden knowledge referred to A set of databases

from different
An approach to a
problem that is not
Information that is None of these
hidden in a
c
vendors, possibly guaranteed to work database and that
using different but performs well cannot be
database in most cases recovered by a
paradigms simple SQL query.
3 Enrichment is A stage of the KDD
process in which
The process of
finding a solution
The distance
between two points
None of these
a
new data is added for a problem as calculated using
to the existing simply by the Pythagoras
selection enumerating all theorem
possible solutions
according to some
pre-defined order
and then testing
them
4 A dissimilarity coefficient is metric if it meets TRUE

the four metric properties, including the
FALSE Both a & b None of these
a
triangular inequality for all possible triplets
of points in the D matrix
5 A dissimilarity coefficient is semimetric if it
violates the triangular inequality for all
TRUE FALSE Both a & b None of these
b
possible triplets of point in D matrix
6 A D coefficient is Euclidean if it always

produces D matrices that can be fully
a
represented in Euclidean space without
distortion
7 A non- Euclidean dissimilarity matrix is
identified by the criterion that principal
a
coordinate analysis (PCoA) of that matrix
produces some negative eigenvalues
8 Ecologists prefer to remove double zeros
from the calculation of (dis)similarity
a
coefficients because double zeros have no
clear, unambiguous ecological interpretation
9 In double-zerosymmetrical coefficients, like TRUE
the simple matching coefficient, double zeros
a
affect the S or D value
10 Plane which have set of points satisfying

certain relationships, expressible in terms of
Euclidean Plane Dihedral plane one dimensional
plane
zero plane
a
distance and angle is known as
11 Which of the following distance metric can

not be used in k-NN?
Manhattan Minkowski Tanimoto All of these
d
12 Which of the following is true about

Manhattan distance?
It can be used for
continuous
It can be used for
categorical
It can be used for None of these
categorical as well
a
variables variables as continuous
13 1 2 4 8
Which of the following will be Euclidean
Distance between the two data point A(1,3)
a
and B(2,3)?
14 Suppose, you want to predict the class of new + Class
data point x=1 and y=1 using eucludian
– Class cant say None of these
a
distance in 3-NN. In which class this data
point belong to?
15 Which of the following would be the leave on (2/14)
out cross validation accuracy for k=5?
(4/14) (6/14) None of these
d
16 What is Manhattan distance? The distance The distance
between two points between two points
The distance
between two points
None of these
c
in a vector data in a raster data in a raster data
layer calculated as layer calculated as layer calculated as
the length of the the number of cells the sum of the cell
line between them. crossed by a sides intersected by
straight line a straight line
between them. between them.
17 Which of the following combination is
incorrect ?
Continuous – Continuous –
euclidean distance correlation
Binary –
manhattan
None of the
Mentioned
d
similarity distance
18 The two-dimensional Euclidean plane is

known as
Euclidean Plane Dihedral plane one dimensional
plane
zero plane
a
19 The standardised form of Euclidean distance Manhattan
is called as distance
Mahalanobis
distance
Dendogram none of these
b
20 The distance between two points calculated

using Pythagoras theorem is
Manhattan Minkowski Tanimoto Euclidean
d
21 Identify the example of Nominal attribute Temprature salary mass gender
d
22 Nominal and ordinal attributes can be
collectively referred to as_________ attributes
Perfect Qualitative Consistant Optimized
b
23 A similarity S and a dissimilarity D matrix

have zeros on the main diagonal
b
24 The distance between species profilesand the TRUE
Hellinger, chord,and chi-square distancesare
a
Euclidean indices
25 In most cases, sqrt(D) or sqrt(1–S) turns a

non-Euclidean matrix to Euclidean
a
26 For descriptors withdifferent physical units, TRUE

the Euclidean distance computed on
a
standardized descriptors makes sense;the
distances then have no physical units
27 A non-Euclidean dissimilarity matrix is

identified by the criterion hat principal
a
coordinate analysis (PCoA)of that matrix
produces some negative eigenvalues
28 A D coefficient is Euclidean if it always

produces D matrices that can be fully
a
represented in Euclidean space without
distortion
29 A similarity S and a dissimilarity D matrix
have zeros on the main diagonal
b
30 …..are the different types of attributes nominal ordinal interval All of these
d
31 … are the types of data sets graph record ordered All of these
d
32 …are the types of ordered data spatial data temporal data sequential data All of these
d
33 … are the example of data quality problems missing value wrong data duplicate data All of these
d
34 Numerical measure of how different two
data objects are…
similarity measure dissimilarity
measure
Both a & b none of these
b
35 Numerical measure of how same two data

objects are…
similarity measure dissimilarity
measure
Both a & b none of these
a
36 Combining two or more attributes (or

objects) into a single attribute (or object)
Aggregation Sampling Transformation none of these
a
37 Which of the following is true about

Manhattan distance?
It can be used for
continuous
It can be used for
categorical
It can be used for None of these
categorical as well
a
variables variables as continuous
38 Sampling is the main technique employed

for data reduction
Aggregation Sampling Transformation none of these
b
39 …is the process of converting a continuous

attribute into an ordinal attribute
Discretization Sampling Transformation none of these
a
FOUR
Sr. No. Questions a b c d Ans
1 What does Apriori algorithm do? It mines all

frequent
It mines all
frequent patterns
Both a and b None of these
a
patterns through through pruning
pruning rules rules with higher
with lesser suppor
2 What does FP growth algorithm do? It mines all
frequent
It mines all
frequent patterns
It mines all
frequent
All of these
c
patterns through through pruning patterns by
pruning rules rules with higher constructing a FP
with lesser support tree
support
3 What techniques can be used to improve the

efficiency of apriori algorithm?
hash based
techniques
transaction
reduction
Partitioning All of these
d
4 What do you mean by support(A)? Total number of Total Number of

transactions transactions not
Number of
transactions
Number of
transactions not
c
containing A containing A containing A / containing A /
Total number of Total number of
transactions transactions
5 Which of the following is direct application of Social Network

frequent itemset mining? Analysis
Market Basket
Analysis
outlier detection intrusion
detection
b
6 What is not true about FP growth algorithms? It mines frequent
itemsets without
There are
chances that FP
FP trees are very It expands the
expensive to original database
d
candidate trees may not fit build to build FP trees
generation in the memory
7 When do you consider an association rule
interesting?
If it only satisfies If it only satisfies If it satisfies both There are other
min_support min_confidence min_support and measures to
c
min_confidence check so
8 What is the difference between absolute and

relative support?
Absolute
-Minimum
Absolute-Minimu Both a and b
m support
None of these
a
support count threshold and
threshold and Relative-Minimu
Relative-Minimu m support count
m support threshold
9 Ahcandidate
h ld
What is the relation between candidate and
frequent itemsets? itemset is always
A frequent No relation
itemset must be a between the two
None of these
b
a frequent candidate itemset
itemset
10 Which technique finds the frequent itemsets
in just two database scans?
Patitioning sampling hashing None of these
a
11 Which of the following is true? Both apriori and
FP-Growth uses
Both apriori and Both a and b
FP-Growth uses
None of these
a
horizontal data vertical data
format format
12 What is the principle on which Apriori

algorithm work?
If a rule is
infrequent, its
If a rule is
infrequent, its
a
specialized rules generalized rules
are also are also
infrequent infrequent
13 Which of these is not a frequent pattern
mining algorithm
Apriori FP growth Decision trees Eclat
c
14 Which algorithm requires fewer scans of

data?
Apriori FP growth Both a and b None of these
b
15 What are Max_confidence, Cosine similarity,
All_confidence?
Frequent pattern Measures to
mining improve
Pattern
evaluation
None of these
c
algorithms efficiency of measure
apriori
16 What are closed itemsets? An itemset for
which at least
An item setwhose
no proper super-
b
one proper itemset has same
supert itemset support
has same support
17 What are closed frequent itemsets? A closed itemset A frequent

itemset
An itemset which None of these
is both closed
c
and frequent
18 What are maximal frequent itemsets? A frequent

itemsetwhose no
A frequent
itemset whose
a
super-itemset is super-itemset is
frequent also frequent
19 Why is correlation analysis important? To make apriori To weed out

memory efficient uninteresting
To find large
number of
To restrict the
number of
b
frequent itemsets interesting database
itemsets iterations
20 What will happen if support is reduced? Number of Some itemsets
frequent itemsets will add to the
Some itemsets
will become
Can not say
b
remains same current set of infrequent while
frequent itemsets others will
become frequent
21 Can FP growth algorithm be used if FP tree
cannot be fit in memory?
Yes No Both a and b None of these
b
22 What is association rule mining? Same as frequent Finding of strong Both a and b
itemset mining association rules
None of these
b
using frequent
itemsets
23 What is frequent pattern growth? Same as frequent Use of hashing to

itemset mining make discovery
Mining of
frequent itemsets
None of these
c
of frequent without
itemsets more candidate
efficient generation
24 When is sub-itemset pruning done? A frequent
itemset 'P' is a
Support (P) =
Support(Q)
When both a and When a is true
b is true and b is not
c
proper subset of
another frequent
itemset 'Q'
25 Which of the following is not null invariant

measure(that does not considers null
all_confidence max_confidence cosine measure lift
d
transactions)?
26 The apriori algorithm works in
a ..and ..fashion?
top-down and
depth-first
top-down and
breath-first
bottom-up and
depth-first
bottom-up and
breath-first
d
27 Our use of association analysis will yield the TRUE
same frequent itemsets and strong association
FALSE Both a and b None of these
a
rules whether a specific item occurs once or
three times in an individual transaction
28 In association rule mining the generation of

the frequent itermsets is the computational
TRUE FALSE Both a and b None of these
a
intensive step.
29 The number of iterations in apriori __________ increases with
the size of the
decreases with
the increase in
increases with
the size of the
decreases with
increase in size
c
data size of the data maximum of the maximum
frequent set frequent set
30 Which of the following are interestingness

measures for association rules?
recall lift accuracy compactness
b
31 Frequent item sets is Superset of only Superset of only Subset of

closed frequent maximal maximal
Superset of both
closed frequent
d
item sets frequent item sets frequent item item sets and
sets maximal
frequent item
sets
32 63 30 38 70
Assume that we have a dataset containing
information about 200 individuals. A
c
supervised data mining session has
discovered the following rule: IF age < 30 &
credit card insurance = yes THEN life
insurance = yes Rule Accuracy: 70% and Rule
Coverage: 63% How many individuals in the
class life insurance= no have credit card
insurance and are less than 30 years old?
33 100 4950 200 5000

In Apriori algorithm, if 1 item-sets are 100,
then the number of candidate 2 item-sets are
b
34 Significant Bottleneck in the Apriori

algorithm is
Finding frequent pruning
itemsets
Candidate
generation
Number of
iterations
c
35 Which Association Rule would you prefer High support and High support and Low support and Low support and
medium low confidence high confidence low confidence
c
confidence
36 The apriori property means If a set cannot
pass a test, its
To decrease the
efficiency, do
To improve the
efficiency, do
If a set can pass a
test, its supersets
a
supersets will level-wise level-wise will fail the same
also fail the same generation of generation of test
test frequent item sets frequent item
37 sets
If an item set ‘XYZ’ is a frequent item set, then undefined
all subsets of that frequent item set are
not frequent frequent cant say
c
38 To determine association rules from frequent Only minimum
item sets confidence
Neither support
not confidence
Both minimum
support and
Minimum
support is needed
c
needed needed confidence are
needed
39 If {A,B,C,D} is a frequent itemset, candidate

rules which is not possible is
C –> A D –> ABCD A –> BC B –> ADC
b
40 What is frequent pattern growth? Same as frequent Use of hashing to

itemset mining make discovery
Mining of
frequent itemsets
None of these
c
of frequent without
itemsets more candidate
efficient generation
FIVE
No.
1 Data set {brown, black, blue, green , red} is example of Select one: a.
Continuous
b. Ordinal
attribute
c.
Numeric
B
attribute attribute
2 Which of the following activities is NOT a data mining task? Select

one:
a. Predicting
the future
b.
Monitoring
c.
Extracti
d.
Monitor
C
stock price of and ng the ing the
a company predicting frequen heart
using failures in a cies of a rate of a
historical hydropower sound patient
records plant wave for
abnorm
alities
3 The difference between supervised learning and unsupervised

learning is given by
a. unlike
unsupervise
b. unlike
unsupervise
c. there
is no
d. unlike
supervis
A
d learning, d learning, differen ed
supervised supervised ce leaning,
learning learning unsuper
needs can be used vised
labeled data to detect learning
outliers can
form
new
classes
4 Regression analysis is a form of predictive modelling technique TRUE FALSE
A
5 Regression analysis is a form of predictive modelling technique
which investigates the relationship between
TRUE FALSE
A
a dependent (target) and independent variable (s) (predictor).
6 Logistic regression should be used when the dependent variable is
binary (0/ 1, True/ False, Yes/ No) in nature.
TRUE FALSE
A
7 Decision Tree is used to build classification and regression models. TRUE FALSE
A
8 Sequential Covering Algorithm can be used to
extract___________rules form the training data
Do_WHILE IF-THEN
B
9 Bayesian Belief Network or Bayesian Network or Belief Network is TRUE

a Probabilistic Graphical Model (PGM) that represents conditional
FALSE
A
dependencies between random variables through a Directed Acyclic
Graph (DAG).
10 In k-NN classification, the output is a class membership. TRUE FALSE
A
11 Associative classification integrates _______________ and association Regression
rule discovery to build classification models (classifiers).
classificatio
n
B
12 BAYESIAN BELIEF NETWORKS To represent the probabilistic

relationships between different classes.
TRUE FALSE
A
13 Regression analysis is a form of _______________ modelling

technique
definate predictive
B
14 Regression analysis is used for forecasting, time series modelling
and finding the causal effect relationship between the variables.
TRUE FALSE
A
15 Logistic regression should be used when the ___________ variable is

independent dependent
B
16 In k-NN regression, the output is the property value for the object. TRUE FALSE
A
17 Decision Tree Mining belongs to supervised class learning. TRUE FALSE
A
18 A regression equation is a polynomial regression equation if the
power of independent variable is more than 1.
TRUE FALSE
A
19 Decision Tree is used to create data models that will predict class
labels or values for the decision-making process.
TRUE FALSE
A
20 Regression indicates the significant relationships between

dependent variable and independent variable.
TRUE FALSE
A
21 Decision Tree Mining belongs to _________________class learning. supervised unsupervise

d
A
22 A decision tree works for both discrete and continuous variables. TRUE FALSE
A
23 Decision tree induction is the method of learning the decision trees TRUE
from the training set.
FALSE
A
24 Case-Based Reasoning (CBR) is used to solve problems by finding

similar, past cases and adapting their solutions.
TRUE FALSE
A
25 The Case-based reasoning CBR process can be described as a cyclic

procedure
TRUE FALSE
A
26 Linear Regression establishes a relationship between dependent
variable (Y) and one or more independent variables (X) using a best
TRUE FALSE
A
fit straight line (also known as regression line).
27 Case-based reasoning (CBR) is the process of solving new problems TRUE

based on the solutions of similar past problems.[
FALSE
A
28 Sequential Covering Algorithm can be used to extract IF-THEN rules TRUE

form the training data
FALSE
A
29 The Case-based reasoning CBR process can be described as a

_________procedure
cyclic Random acyclic none
A
30 Frequent patterns are itemsets, subsequences, or substructures that TRUE
appear in a data set with frequency no less than a user-specified
FALSE
A
threshold.
31 An associative classifier (AC) is a kind of supervised learning model TRUE
that uses association rules to assign a target value.
FALSE
A
32 Regression indicates the significant relationships between

dependent variable and independent variable.
TRUE FALSE
A
33 Decision Tree Mining belongs to _________________class learning. supervised unsupervise
d
A
34 Regression analysis is used for forecasting, time series modelling
and finding the causal effect relationship between the variables.
TRUE FALSE
A
35 Logistic regression should be used when the ___________ variable is

independent dependent
B
36 Case-based reasoning (CBR) is an experience-based approach to

solving new problems by adapting previously successful solutions
TRUE FALSE
A
to similar problems.
37 Regression and classification are categorized under the same
umbrella of supervised machine learning.
TRUE FALSE
A
38 Regression and classification are categorized under_____________

machine learning.
supervised
unsupervise
A
d
39 K-NN is a lazy learner because it doesn't learn a discriminative
function from the training data but “memorizes” the training
TRUE FALSE
A
dataset instead
40 In machine learning, lazy learning is a learning method in which
generalization of the training data is, in theory, delayed until a
TRUE FALSE
A
query is made to the system
SIX
No.
1 The problem of finding hidden structure in
unlabeled data is called
Supervised learning Unsupervised
learning
Reinforcemen none of the
t learning above
b
2 Which of the following is true for Classification? A subdivision of a set A measure of the
accuracy
The task of
assigning a
All of these
a
classification
3 Classification and regression are the properties data manipulation

of…
data mining both A & B none of the
above
b
4 We define a ______ as a subdivison of a set of

examples into a number of classes
kingdom tree classification array
c
5 What is inductive learning? learning by

hypothesis
learning by
analyzing
learning by
generalizing
none of these
c
6 In a multiclass classification problem, Bayes

classifier assigns an instance to the class
Highest aposteriori
probability
Highest apriori
probability
Lowest
aposteriori
none of these
c
corresponding to: probability
7 Multiclass classifiers are also known as: Mutlilabel classifiers Multinomial

classifiers
Multioutput
classifiers
none of these
b
8 Task of inferring a model from labeled training Unsupervised

data is called learning
Supervised learning Reinforcemen none of these
t learning
b

unlabeled data is called unsupervised learning
TRUE FALSE
a
unlabeled data is called supervised learning
TRUE FALSE
b
11 Multiclass classifiers are also known as
Multinomial classifiers
TRUE FALSE
a
12 Task of inferring a model from labeled training TRUE
data is called Supervised learning
FALSE
a
13 Classification is A subdivision of a set
of examples into a
A measure of the
accuracy, of the
The task of
assigning a
None of these
a
number of classes classification of a classification
concept that is given to a set of
by a certain theory examples
14 Classification is A subdivision of a set of
examples into a number of classes
TRUE FALSE
a
15 Task of inferring a model from labeled training TRUE
data is called Unsupervised learning
FALSE
b
16 Classification accuracy is A subdivision of a set Measure of the

of examples into a accuracy, of the
The task of
assigning a
None of these
b
17 Classification task referred to A subdivision of a set A measure of the
of examples into a accuracy, of the
The task of
assigning a
None of these
c
18 Hybrid learning is Machine-learning The learning Learning by
involving different algorithmic analyzes generalizing
None of these
a
techniques the examples on a from
systematic basis and examples
makes incremental
adjustments to the
theory that is
learned
19 Incremental learning referred to Machine-learning
involving different
The learning Learning by
algorithmic analyzes generalizing
None of these
b
makes incremental
adjustments to the
theory that is
learned
20 Learning is The process of

finding the right
It automatically
maps an external
A process
where an
None of these
c
formal signal space into a individual
representation of a system's internal learns how to
certain body of representational carry out a
knowledge in order space. They are certain task
to represent it in a useful in the when making
knowledge-based performance of a transition
system classification tasks. from a
situation in
which the task
cannot be
carried out to
a situation in
which the
same task
under the
same
circumstances
can be carried
out.
21 Classification accuracy is Measure of the
accuracy, of the classification of a concept that is
TRUE FALSE
a
given by a certain theory
22 Learning algorithm referrers to An algorithm that
can learn
A sub-discipline of
computer science
A
machine-learn
None of these
a
that deals with the ing approach
design and that abstracts
implementation of from the
learning algorithms actual strategy
of an
individual
algorithm and
can therefore
be applied to
any other
form of
machine
learning.
23 Inductive learning is Machine-learning

involving different
The learning Learning by
algorithmic analyzes generalizing
None of these
c
makes incremental
adjustments to the
theory that is
learned
24 Bayesian classifiers is A class of learning
algorithm that tries
Any mechanism
employed by a
An approach
to the design
None of these
a
to find an optimum learning system to of learning
classification of a set constrain the search algorithms
of examples using space of a hypothesis that is
the probabilistic inspired by
theory. the fact that
when people
encounter
new
situations,
they often
explain them
by reference
to familiar
experiences,
adapting the
explanations
to fit the new
situation.
25 Reinforcement learning is based on
goal-directed learning from interaction
TRUE FALSE
a
26 Classification and regression are the properties TRUE
Of data mining
FALSE
a
27 Multi-perspective learning is needed for
multi-perspective decision making.
TRUE FALSE
a
28 Types of Learning Supervised learning Unsupervised
learning
both A & B none of these
c
29 In reinforcement learning,a reward

function that is used to define goal in a
TRUE FALSE
a
reinforcement learning problem.
30 In reinforcement learning,a value function that TRUE
is used to define goal in a reinforcement
FALSE
b
learning problem.
31 In Supervised learning the decision is made on TRUE
the initial input or the input given at the start
FALSE
a
32 Chess game is example of reinforcement
learning
TRUE FALSE
a
33 Chess game is example of supervised learning TRUE FALSE

b
34 In Reinforcement learning decision is
dependent
TRUE FALSE
a
35 Supervised learning the decisions are
independent of each other
TRUE FALSE
a
36 Supervised learning the decisions are
independent of each other so labels are given to
TRUE FALSE
a
each decision
37 Supervised learning the decisions are --------of
each other so labels are given to each decision.
independent dependent both A & B none of these
a
38 Reward and value function is sub elements of

reinforcement learning
TRUE FALSE
a
39 Reward and value function is not sub elements TRUE

of reinforcement learning
FALSE
b
40 Object recognition is example of supervised

learning
TRUE FALSE
a
SUB : 410244(D) DMW
Data Mining and Warehouse MCQS with Answer

Multiple Choice Questions.
1. __________ is a subject-oriented, integrated, time-variant, nonvolatile collection of data in support
of
management decisions.
A. Data Mining.
B. Data Warehousing.
C. Web Mining.
D. Text Mining.
ANSWER: B
2. The data Warehouse is__________.
A. read only.
B. write only.
C. read write only.
D. none.
ANSWER: A
3. Expansion for DSS in DW is__________.
A. Decision Support system.
B. Decision Single System.
C. Data Storable System.
D. Data Support System.
ANSWER: A
4. The important aspect of the data warehouse environment is that data found within the data
warehouse
is___________.
A. subject-oriented.
B. time-variant.
C. integrated.
D. All of the above.
ANSWER: D
5. The time horizon in Data warehouse is usually __________.
A. 1-2 years.
B. 3-4years.
C. 5-6 years.
D. 5-10 years.
ANSWER: D
6. The data is stored, retrieved & updated in ____________.
A. OLAP.
B. OLTP.
C. SMTP.
D. FTP.
ANSWER: B
7. __________describes the data contained in the data warehouse.
A. Relational data.
B. Operational data.
C. Metadata.
D. Informational data.
ANSWER: C
8. ____________predicts future trends & behaviors, allowing business managers to make proactive,
knowledge-driven decisions.
A. Data warehouse.
SUB : 410244(D) DMW
B. Data mining.
C. Datamarts.
D. Metadata.
ANSWER: B
9. __________ is the heart of the warehouse.
A. Data mining database servers.
B. Data warehouse database servers.
C. Data mart database servers.
D. Relational data base servers.
ANSWER: B
10. ________________ is the specialized data warehouse database.
A. Oracle.
B. DBZ.
C. Informix.
D. Redbrick.
ANSWER: D
11. ________________defines the structure of the data held in operational databases and used by
operational applications.
A. User-level metadata.
B. Data warehouse metadata.
C. Operational metadata.
D. Data mining metadata.
ANSWER: C
12. ________________ is held in the catalog of the warehouse database system.
A. Application level metadata.
B. Algorithmic level metadata.
C. Departmental level metadata.
D. Core warehouse metadata.
ANSWER: B
13. _________maps the core warehouse metadata to business concepts, familiar and useful to end
users.
B. User level metadata.
C. Enduser level metadata.
D. Core level metadata.
ANSWER: A
14. ______consists of formal definitions, such as a COBOL layout or a database schema.
A. Classical metadata.
B. Transformation metadata.
C. Historical metadata.
D. Structural metadata.
ANSWER: A
15. _____________consists of information in the enterprise that is not in classical form.
A. Mushy metadata.
B. Differential metadata.
C. Data warehouse.
D. Data mining.
ANSWER: A
16. . ______________databases are owned by particular departments or business groups.
A. Informational.
B. Operational.
C. Both informational and operational.
D. Flat.
SUB : 410244(D) DMW
ANSWER: B
17. The star schema is composed of __________ fact table.
A. one.
B. two.
C. three.
D. four.
ANSWER: A
18. The time horizon in operational environment is ___________.
A. 30-60 days.
B. 60-90 days.
C. 90-120 days.
D. 120-150 days.
ANSWER: B
19. The key used in operational environment may not have an element of__________.
A. time.
B. cost.
C. frequency.
D. quality.
ANSWER: A
20. Data can be updated in _____environment.
A. data warehouse.
B. data mining.
C. operational.
D. informational.
ANSWER: C
21. Record cannot be updated in _____________.
A. OLTP
B. files
C. RDBMS
D. data warehouse
ANSWER: D
22. The source of all data warehouse data is the____________.
A. operational environment.
B. informal environment.
C. formal environment.
D. technology environment.
ANSWER: A
23. Data warehouse contains_____________data that is never found in the operational
environment.
A. normalized.
B. informational.
C. summary.
D. denormalized.
ANSWER: C
24. The modern CASE tools belong to _______ category.
A. a. analysis.
B. b.Development
C. c.Coding
D. d.Delivery
ANSWER: A
25. Bill Inmon has estimated___________of the time required to build a data warehouse, is
consumed in
the conversion process.
SUB : 410244(D) DMW
A. 10 percent.
B. 20 percent.
C. 40 percent
D. 80 percent.
ANSWER: D
26. Detail data in single fact table is otherwise known as__________.
A. monoatomic data.
B. diatomic data.
C. atomic data.
D. multiatomic data.
ANSWER: C
27. _______test is used in an online transactional processing environment.
A. MEGA.
B. MICRO.
C. MACRO.
D. ACID.
ANSWER: D
28. ___________ is a good alternative to the star schema.
A. Star schema.
B. Snowflake schema.
C. Fact constellation.
D. Star-snowflake schema.
ANSWER: C
29. The biggest drawback of the level indicator in the classic star-schema is that it limits_________.
A. quantify.
B. qualify.
C. flexibility.
D. ability.
ANSWER: C
30. A data warehouse is _____________.
A. updated by end users.
B. contains numerous naming conventions and formats
C. organized around important subject areas.
D. contains only current data.
ANSWER: C
31. An operational system is _____________.
A. used to run the business in real time and is based on historical data.
B. used to run the business in real time and is based on current data.
C. used to support decision making and is based on current data.
D. used to support decision making and is based on historical data.
ANSWER: B
32. The generic two-level data warehouse architecture includes __________.
A. at least one data mart.
B. data that can extracted from numerous internal and external sources.
C. near real-time updates.
D. far real-time updates.
ANSWER: C
33. The active data warehouse architecture includes __________
D. all of the above.
ANSWER: D
SUB : 410244(D) DMW
34. Reconciled data is ___________.
A. data stored in the various operational systems throughout the organization.
B. current data intended to be the single source for all decision support systems.
C. data stored in one operational system in the organization.
D. data that has been selected and formatted for end-user support applications.
ANSWER: B
35. Transient data is _____________.
A. data in which changes to existing records cause the previous version of the records to be
eliminated.
B. data in which changes to existing records do not cause the previous version of the records to be
eliminated.
C. data that are never altered or deleted once they have been added.
D. data that are never deleted once they have been added.
ANSWER: A
36. The extract process is ______.
A. capturing all of the data contained in various operational systems.
B. capturing a subset of the data contained in various operational systems.
C. capturing all of the data contained in various decision support systems.
D. capturing a subset of the data contained in various decision support systems.
ANSWER: B
37. Data scrubbing is _____________.
A. a process to reject data from the data warehouse and to create the necessary indexes.
B. a process to load the data in the data warehouse and to create the necessary indexes.
C. a process to upgrade the quality of data after it is moved into a data warehouse.
D. a process to upgrade the quality of data before it is moved into a data warehouse
ANSWER: D
38. The load and index is ______________.
D. a process to upgrade the quality of data before it is moved into a data warehouse.
ANSWER: B
39. Data transformation includes __________.
A. a process to change data from a detailed level to a summary level.
B. a process to change data from a summary level to a detailed level.
C. joining data from one source into various sources of data.
D. separating data from one source into various sources of data.
ANSWER: A
40. ____________ is called a multifield transformation.
A. Converting data from one field into multiple fields.
B. Converting data from fields into field.
C. Converting data from double fields into multiple fields.
D. Converting data from one field to one field.
ANSWER: A
41. The type of relationship in star schema is __________________.
A. many-to-many.
B. one-to-one.
C. one-to-many.
D. many-to-one.
ANSWER: C
42. Fact tables are ___________.
A. completely demoralized.
B. partially demoralized.
SUB : 410244(D) DMW
C. completely normalized.
D. partially normalized.
ANSWER: C
43. _______________ is the goal of data mining.
A. To explain some observed event or condition.
B. To confirm that data exists.
C. To analyze data for expected relationships.
D. To create a new data warehouse.
ANSWER: A
44. Business Intelligence and data warehousing is used for ________.
A. Forecasting.
B. Data Mining.
C. Analysis of large volumes of product sales data.
ANSWER: D
45. The data administration subsystem helps you perform all of the following, except__________.
A. backups and recovery.
B. query optimization.
C. security management.
D. create, change, and delete information.
ANSWER: D
46. The most common source of change data in refreshing a data warehouse is _______.
A. queryable change data.
B. cooperative change data.
C. logged change data.
D. snapshot change data.
ANSWER: A
47. ________ are responsible for running queries and reports against data warehouse tables.
A. Hardware.
B. Software.
C. End users.
D. Middle ware.
ANSWER: C
48. Query tool is meant for __________.
A. data acquisition.
B. information delivery.
C. information exchange.
D. communication.
ANSWER: A
49. Classification rules are extracted from _____________.
A. root node.
B. decision tree.
C. siblings.
D. branches.
ANSWER: B
50. Dimensionality reduction reduces the data set size by removing ____________.
A. relevant attributes.
B. irrelevant attributes.
C. derived attributes.
D. composite attributes.
ANSWER: B
51. ___________ is a method of incremental conceptual clustering.
A. CORBA.
SUB : 410244(D) DMW
B. OLAP.
C. COBWEB.
D. STING.
ANSWER: C
52. Effect of one attribute value on a given class is independent of values of other attribute is called
_________.
A. value independence.
B. class conditional independence.
C. conditional independence.
D. unconditional independence.
ANSWER: A
53. The main organizational justification for implementing a data warehouse is to provide ______.
A. cheaper ways of handling transportation.
B. decision support.
C. storing large volume of data.
D. access to data.
ANSWER: C
54. Multidimensional database is otherwise known as____________.
A. RDBMS
B. DBMS
C. EXTENDED RDBMS
D. EXTENDED DBMS
ANSWER: B
55. Data warehouse architecture is based on ______________.
A. DBMS.
B. RDBMS.
C. Sybase.
D. SQL Server.
ANSWER: B
56. Source data from the warehouse comes from _______________.
A. ODS.
B. TDS.
C. MDDB.
D. ORDBMS.
ANSWER: A
57. ________________ is a data transformation process.
A. Comparison.
B. Projection.
C. Selection.
D. Filtering.
ANSWER: D
58. The technology area associated with CRM is _______________.
A. specialization.
B. generalization.
C. personalization.
D. summarization.
ANSWER: C
59. SMP stands for _______________.
A. Symmetric Multiprocessor.
B. Symmetric Multiprogramming.
C. Symmetric Metaprogramming.
D. Symmetric Microprogramming.
ANSWER: A
SUB : 410244(D) DMW
60. __________ are designed to overcome any limitations placed on the warehouse by the nature of
the
relational data model.
A. Operational database.
B. Relational database.
C. Multidimensional database.
D. Data repository.
ANSWER: C
61. __________ are designed to overcome any limitations placed on the warehouse by the nature of
the
D. Data repository.
ANSWER: C
62. MDDB stands for ___________.
A. multiple data doubling.
B. multidimensional databases.
C. multiple double dimension.
D. multi-dimension doubling.
ANSWER: B
63. ______________ is data about data.
A. Metadata.
B. Microdata.
C. Minidata.
D. Multidata.
ANSWER: A
64. ___________ is an important functional component of the metadata.
A. Digital directory.
B. Repository.
C. Information directory.
D. Data dictionary.
ANSWER: C
65. EIS stands for ______________.
A. Extended interface system.
B. Executive interface system.
C. Executive information system.
D. Extendable information system.
ANSWER: C
66. ___________ is data collected from natural systems.
A. MRI scan.
B. ODS data.
C. Statistical data.
D. Historical data.
ANSWER: A
67. _______________ is an example of application development environments.
A. Visual Basic.
B. Oracle.
C. Sybase.
D. SQL Server.
ANSWER: A
68. The term that is not associated with data cleaning process is ______.
SUB : 410244(D) DMW
A. domain consistency.
B. deduplication.
C. disambiguation.
D. segmentation.
ANSWER: D
69. ____________ are some popular OLAP tools.
A. Metacube, Informix.
B. Oracle Express, Essbase.
C. HOLAP.
D. MOLAP.
ANSWER: A
70. Capability of data mining is to build ___________ models.
A. retrospective.
B. interrogative.
C. predictive.
D. imperative.
ANSWER: C
71. _____________ is a process of determining the preference of customer's majority.
A. Association.
B. Preferencing.
C. Segmentation.
D. Classification.
ANSWER: B
72. Strategic value of data mining is ______________.
A. cost-sensitive.
B. work-sensitive.
C. time-sensitive.
D. technical-sensitive.
ANSWER: C
73. ____________ proposed the approach for data integration issues.
A. Ralph Campbell.
B. Ralph Kimball.
C. John Raphlin.
D. James Gosling.
ANSWER: B
74. The terms equality and roll up are associated with ____________.
A. OLAP.
B. visualization.
C. data mart.
D. decision tree.
ANSWER: C
75. Exceptional reporting in data warehousing is otherwise called as __________.
A. exception.
B. alerts.
C. errors.
D. bugs.
ANSWER: B
76. ____________ is a metadata repository.
A. Prism solution directory manager.
B. CORBA.
C. STUNT.
D. COBWEB.
ANSWER: A
SUB : 410244(D) DMW
77. ________________ is an expensive process in building an expert system.
A. Analysis.
B. Study.
C. Design.
D. Information collection.
ANSWER: D
78. The full form of KDD is _________.
A. Knowledge database.
B. Knowledge discovery in database.
C. Knowledge data house.
D. Knowledge data definition.
ANSWER: B
79. The first International conference on KDD was held in the year _____________.
A. 1996.
B. 1997.
C. 1995.
D. 1994.
ANSWER: C
80. Removing duplicate records is a process called _____________.
A. recovery.
B. data cleaning.
C. data cleansing.
D. data pruning.
ANSWER: B
81. ____________ contains information that gives users an easy-to-understand perspective of the
information stored in the data warehouse.
A. Business metadata.
B. Technical metadata.
D. Financial metadata.
ANSWER: A
82. _______________ helps to integrate, maintain and view the contents of the data warehousing
system.
A. Business directory.
B. Information directory.
C. Data dictionary.
D. Database.
ANSWER: B
83. Discovery of cross-sales opportunities is called ________________.
A. segmentation.
B. visualization.
C. correction.
D. association.
ANSWER: D
84. Data marts that incorporate data mining tools to extract sets of data are called ______.
A. independent data mart.
B. dependent data marts.
C. intra-entry data mart.
D. inter-entry data mart.
ANSWER: B
85. ____________ can generate programs itself, enabling it to carry out new tasks.
A. Automated system.
B. Decision making system.
SUB : 410244(D) DMW
C. Self-learning system.
D. Productivity system.
ANSWER: D
86. The power of self-learning system lies in __________.
A. cost.
B. speed.
C. accuracy.
D. simplicity.
ANSWER: C
87. Building the informational database is done with the help of _______.
A. transformation or propagation tools.
B. transformation tools only.
C. propagation tools only.
D. extraction tools.
ANSWER: A
88. How many components are there in a data warehouse?
A. two.
B. three.
C. four.
D. five.
ANSWER: D
89. Which of the following is not a component of a data warehouse?
A. Metadata.
B. Current detail data.
C. Lightly summarized data.
D. Component Key.
ANSWER: D
90. ________ is data that is distilled from the low level of detail found at the current detailed leve.
A. Highly summarized data.
B. Lightly summarized data.
C. Metadata.
D. Older detail data.
ANSWER: B
91. Highly summarized data is _______.
A. compact and easily accessible.
B. compact and expensive.
C. compact and hardly accessible.
D. compact.
ANSWER: A
92. A directory to help the DSS analyst locate the contents of the data warehouse is seen in ______.
A. Current detail data.
C. Metadata.
ANSWER: C
93. Metadata contains atleast _________.
A. the structure of the data.
B. the algorithms used for summarization.
C. the mapping from the operational environment to the data warehouse.
ANSWER: D
94. Which of the following is not a old detail storage medium?
A. Phot Optical Storage.
SUB : 410244(D) DMW
B. RAID.
C. Microfinche.
D. Pen drive.
ANSWER: D
95. The data from the operational environment enter _______ of data warehouse.
B. Older detail data.
D. Highly summarized data.
ANSWER: A
96. The data in current detail level resides till ________ event occurs.
A. purge.
B. summarization.
C. archieved.
ANSWER: D
97. The dimension tables describe the _________.
A. entities.
B. facts.
C. keys.
D. units of measures.
ANSWER: B
98. The granularity of the fact is the _____ of detail at which it is recorded.
A. transformation.
B. summarization.
C. level.
D. transformation and summarization.
ANSWER: C
99. Which of the following is not a primary grain in analytical modeling?
A. Transaction.
B. Periodic snapshot.
C. Accumulating snapshot.
ANSWER: B
100. Granularity is determined by ______.
A. number of parts to a key.
B. granularity of those parts.
C. both A and B.
D. none of the above.
ANSWER: C
101. ___________ of data means that the attributes within a given entity are fully dependent on the
entire
primary key of the entity.
A. Additivity.
B. Granularity.
C. Functional dependency.
D. Dimensionality.
ANSWER: C
102. A fact is said to be fully additive if ___________.
A. it is additive over every dimension of its dimensionality.
B. additive over atleast one but not all of the dimensions.
C. not additive over any dimension.
D. None of the above.
SUB : 410244(D) DMW
ANSWER: A
103. A fact is said to be partially additive if ___________.
ANSWER: B
104. A fact is said to be non-additive if ___________.
ANSWER: C
105. Non-additive measures can often combined with additive measures to create new _________.
A. additive measures.
B. non-additive measures.
C. partially additive.
ANSWER: A
106. A fact representing cumulative sales units over a day at a store for a product is a _________.
A. additive fact.
B. fully additive fact.
C. partially additive fact.
D. non-additive fact.
ANSWER: B
107. ____________ of data means that the attributes within a given entity are fully dependent on the
entire
primary key of the entity.
A. Additivity.
B. Granularity.
C. Functional Dependency.
D. Dependency.
ANSWER: C
108. Which of the following is the other name of Data mining?
A. Exploratory data analysis.
B. Data driven discovery.
C. Deductive learning.
ANSWER: D
109. Which of the following is a predictive model?
A. Clustering.
B. Regression.
C. Summarization.
D. Association rules.
ANSWER: B
110. Which of the following is a descriptive model?
A. Classification.
B. Regression.
C. Sequence discovery.
ANSWER: C
111. A ___________ model identifies patterns or relationships.
A. Descriptive.
SUB : 410244(D) DMW
B. Predictive.
C. Regression.
D. Time series analysis.
ANSWER: A
112. A predictive model makes use of ________.
A. current data.
B. historical data.
C. both current and historical data.
D. assumptions.
ANSWER: B
113. ____________ maps data into predefined groups.
A. Regression.
B. Time series analysis
C. Prediction.
D. Classification.
ANSWER: D
114. __________ is used to map a data item to a real valued prediction variable.
A. Regression.
B. Time series analysis.
C. Prediction.
D. Classification.
ANSWER: B
115. In ____________, the value of an attribute is examined as it varies over time.
A. Regression.
D. Prediction.
ANSWER: B
116. In ________ the groups are not predefined.
A. Association rules.
B. Summarization.
C. Clustering.
D. Prediction.
ANSWER: C
117. Link Analysis is otherwise called as ___________.
A. affinity analysis.
B. association rules.
C. both A & B.
D. Prediction.
ANSWER: C
118. _________ is a the input to KDD.
A. Data.
B. Information.
C. Query.
D. Process.
ANSWER: A
119. The output of KDD is __________.
A. Data.
B. Information.
C. Query.
D. Useful information.
ANSWER: D
120. The KDD process consists of ________ steps.
SUB : 410244(D) DMW
A. three.
B. four.
C. five.
D. six.
ANSWER: C
121. Treating incorrect or missing data is called as ___________.
A. selection.
B. preprocessing.
C. transformation.
D. interpretation.
ANSWER: B
122. Converting data from different sources into a common format for processing is called as
________.
A. selection.
B. preprocessing.
C. transformation.
D. interpretation.
ANSWER: C
123. Various visualization techniques are used in ___________ step of KDD.
A. selection.
B. transformaion.
C. data mining.
D. interpretation.
ANSWER: D
124. Extreme values that occur infrequently are called as _________.
A. outliers.
B. rare values.
C. dimensionality reduction.
ANSWER: A
125. Box plot and scatter diagram techniques are _______.
A. Graphical.
B. Geometric.
C. Icon-based.
D. Pixel-based.
ANSWER: B
126. __________ is used to proceed from very specific knowledge to more general information.
A. Induction.
B. Compression.
C. Approximation.
D. Substitution.
ANSWER: A
127. Describing some characteristics of a set of data by a general model is viewed as
____________
A. Induction.
B. Compression.
C. Approximation.
D. Summarization.
ANSWER: B
128. _____________ helps to uncover hidden information about the data.
A. Induction.
B. Compression.
C. Approximation.
SUB : 410244(D) DMW
D. Summarization.
ANSWER: C
129. _______ are needed to identify training data and desired results.
A. Programmers.
B. Designers.
C. Users.
D. Administrators.
ANSWER: C
130. Overfitting occurs when a model _________.
A. does fit in future states.
B. does not fit in future states.
C. does fit in current state.
D. does not fit in current state.
ANSWER: B
131. The problem of dimensionality curse involves ___________.
A. the use of some attributes may interfere with the correct completion of a data mining task.
B. the use of some attributes may simply increase the overall complexity.
C. some may decrease the efficiency of the algorithm.
ANSWER: D
132. Incorrect or invalid data is known as _________.
A. changing data.
B. noisy data.
C. outliers.
D. missing data.
ANSWER: B
133. ROI is an acronym of ________.
A. Return on Investment.
B. Return on Information.
C. Repetition of Information.
D. Runtime of Instruction
ANSWER: A
134. The ____________ of data could result in the disclosure of information that is deemed to be
confidential.
A. authorized use.
B. unauthorized use.
C. authenticated use.
D. unauthenticated use.
ANSWER: B
135. ___________ data are noisy and have many missing attribute values.
A. Preprocessed.
B. Cleaned.
C. Real-world.
D. Transformed.
ANSWER: C
136. The rise of DBMS occurred in early ___________.
A. 1950's.
B. 1960's
C. 1970's
D. 1980's.
ANSWER: C
137. SQL stand for _________.
A. Standard Query Language.
SUB : 410244(D) DMW
B. Structured Query Language.
C. Standard Quick List.
D. Structured Query list.
ANSWER: B
138. Which of the following is not a data mining metric?
A. Space complexity.
B. Time complexity.
C. ROI.
ANSWER: D
139. Reducing the number of attributes to solve the high dimensionality problem is called as
________.
A. dimensionality curse.
B. dimensionality reduction.
C. cleaning.
D. Overfitting.
ANSWER: B
140. Data that are not of interest to the data mining task is called as ______.
A. missing data.
B. changing data.
C. irrelevant data.
D. noisy data.
ANSWER: C
141. ______ are effective tools to attack the scalability problem.
A. Sampling.
B. Parallelization
C. Both A & B.
ANSWER: C
142. Market-basket problem was formulated by __________.
A. Agrawal et al.
B. Steve et al.
C. Toda et al.
D. Simon et al.
ANSWER: A
143. Data mining helps in __________.
A. inventory management.
B. sales promotion strategies.
C. marketing strategies.
ANSWER: D
144. The proportion of transaction supporting X in T is called _________.
A. confidence.
B. support.
C. support count.
ANSWER: B
145. The absolute number of transactions supporting X in T is called ___________.
A. confidence.
B. support.
C. support count.
ANSWER: C
SUB : 410244(D) DMW
146. The value that says that transactions in D that support X also support Y is called
______________.
A. confidence.
B. support.
C. support count.
ANSWER: A
147. If T consist of 500000 transactions, 20000 transaction contain bread, 30000 transaction contain
jam,
10000 transaction contain both bread and jam. Then the support of bread and jam is _______.
A. 2%
B. 20%
C. 3%
D. 30%
ANSWER: A
148. 7 If T consist of 500000 transactions, 20000 transaction contain bread, 30000 transaction
contain jam,
10000 transaction contain both bread and jam. Then the confidence of buying bread with jam is
_______.
A. 33.33%
B. 66.66%
C. 45%
D. 50%
ANSWER: D
149. The left hand side of an association rule is called __________.
A. consequent.
B. onset.
C. antecedent.
D. precedent.
ANSWER: C
150. The right hand side of an association rule is called _____.
A. consequent.
B. onset.
C. antecedent.
D. precedent.
ANSWER: A
151. Which of the following is not a desirable feature of any efficient algorithm?
A. to reduce number of input operations.
B. to reduce number of output operations.
C. to be efficient in computing.
D. to have maximal code length.
ANSWER: D
152. All set of items whose support is greater than the user-specified minimum support are called as
_____________.
A. border set.
B. frequent set.
C. maximal frequent set.
D. lattice.
ANSWER: B
153. If a set is a frequent set and no superset of this set is a frequent set, then it is called ________.
A. maximal frequent set.
B. border set.
C. lattice.
SUB : 410244(D) DMW
D. infrequent sets.
ANSWER: A
154. Any subset of a frequent set is a frequent set. This is ___________.
A. Upward closure property.
B. Downward closure property.
C. Maximal frequent set.
D. Border set.
ANSWER: B
155. Any superset of an infrequent set is an infrequent set. This is _______.
A. Maximal frequent set.
B. Border set.
C. Upward closure property.
D. Downward closure property.
ANSWER: C
156. If an itemset is not a frequent set and no superset of this is a frequent set, then it is _______.
A. Maximal frequent set
B. Border set.
ANSWER: B
157. A priori algorithm is otherwise called as __________.
A. width-wise algorithm.
B. level-wise algorithm.
C. pincer-search algorithm.
D. FP growth algorithm.
ANSWER: B
158. The A Priori algorithm is a ___________.
A. top-down search.
B. breadth first search.
C. depth first search.
D. bottom-up search.
ANSWER: D
159. The first phase of A Priori algorithm is _______.
A. Candidate generation.
B. Itemset generation.
C. Pruning.
D. Partitioning.
ANSWER: A
160. The second phaase of A Priori algorithm is ____________.
C. Pruning.
D. Partitioning.
ANSWER: C
161. The _______ step eliminates the extensions of (k-1)-itemsets which are not found to be
frequent, from
being considered for counting support.
B. Pruning.
C. Partitioning.
D. Itemset eliminations.
ANSWER: B
162. The a priori frequent itemset discovery algorithm moves _______ in the lattice.
SUB : 410244(D) DMW
A. upward.
B. downward.
C. breadthwise.
D. both upward and downward.
ANSWER: A
163. After the pruning of a priori algorithm, _______ will remain.
A. Only candidate set.
B. No candidate set.
C. Only border set.
D. No border set.
ANSWER: B
164. The number of iterations in a priori ___________.
A. increases with the size of the maximum frequent set.
B. decreases with increase in size of the maximum frequent set.
C. increases with the size of the data.
D. decreases with the increase in size of the data.
ANSWER: A
165. MFCS is the acronym of _____.
A. Maximum Frequency Control Set.
B. Minimal Frequency Control Set.
C. Maximal Frequent Candidate Set.
D. Minimal Frequent Candidate Set.
ANSWER: C
166. Dynamuc Itemset Counting Algorithm was proposed by ____.
A. Bin et al.
B. Argawal et at.
C. Toda et al.
D. Simon et at.
ANSWER: A
167. Itemsets in the ______ category of structures have a counter and the stop number with them.
A. Dashed.
B. Circle.
C. Box.
D. Solid.
ANSWER: A
168. The itemsets in the _______category structures are not subjected to any counting.
A. Dashes.
B. Box.
C. Solid.
D. Circle.
ANSWER: C
169. Certain itemsets in the dashed circle whose support count reach support value during an
iteration
move into the ______.
A. Dashed box.
B. Solid circle.
C. Solid box.
ANSWER: A
170. Certain itemsets enter afresh into the system and get into the _______, which are essentially
the
supersets of the itemsets that move from the dashed circle to the dashed box.
A. Dashed box.
SUB : 410244(D) DMW
B. Solid circle.
C. Solid box.
D. Dashed circle.
ANSWER: D
171. The itemsets that have completed on full pass move from dashed circle to ________.
A. Dashed box.
B. Solid circle.
C. Solid box.
ANSWER: B
172. The FP-growth algorithm has ________ phases.
A. one.
B. two.
C. three.
D. four.
ANSWER: B
173. A frequent pattern tree is a tree structure consisting of ________.
A. an item-prefix-tree.
B. a frequent-item-header table.
C. a frequent-item-node.
D. both A & B.
ANSWER: D
174. The non-root node of item-prefix-tree consists of ________ fields.
A. two.
B. three.
C. four.
D. five.
ANSWER: B
175. The frequent-item-header-table consists of __________ fields.
A. only one.
B. two.
C. three.
D. four.
ANSWER: B
176. The paths from root node to the nodes labelled 'a' are called __________.
A. transformed prefix path.
B. suffix subpath.
C. transformed suffix path.
D. prefix subpath.
ANSWER: D
177. The transformed prefix paths of a node 'a' form a truncated database of pattern which co-occur
with a
is called _______.
A. suffix path.
B. FP-tree.
C. conditional pattern base.
D. prefix path.
ANSWER: C
178. The goal of _____ is to discover both the dense and sparse regions of a data set.
A. Association rule.
B. Classification.
C. Clustering.
D. Genetic Algorithm.
SUB : 410244(D) DMW
ANSWER: C
179. Which of the following is a clustering algorithm?
A. A priori.
B. CLARA.
C. Pincer-Search.
D. FP-growth.
ANSWER: B
180. _______ clustering technique start with as many clusters as there are records, with each
cluster having
only one record.
A. Agglomerative.
B. divisive.
C. Partition.
D. Numeric.
ANSWER: A
181. __________ clustering techniques starts with all records in one cluster and then try to split that
cluster
into small pieces.
A. Agglomerative.
B. Divisive.
C. Partition.
D. Numeric.
ANSWER: B
182. Which of the following is a data set in the popular UCI machine-learning repository?
A. CLARA.
B. CACTUS.
C. STIRR.
D. MUSHROOM.
ANSWER: D
183. In ________ algorithm each cluster is represented by the center of gravity of the cluster.
A. k-medoid.
B. k-means.
C. STIRR.
D. ROCK.
ANSWER: B
184. In ___________ each cluster is represented by one of the objects of the cluster located near
the
center.
A. k-medoid.
B. k-means.
C. STIRR.
D. ROCK.
ANSWER: A
185. Pick out a k-medoid algoithm.
A. DBSCAN.
B. BIRCH.
C. PAM.
D. CURE.
ANSWER: C
186. Pick out a hierarchical clustering algorithm.
A. DBSCAN
B. BIRCH.
C. PAM.
SUB : 410244(D) DMW
D. CURE.
ANSWER: A
187. CLARANS stands for _______.
A. CLARA Net Server.
B. Clustering Large Application RAnge Network Search.
C. Clustering Large Applications based on RANdomized Search.
D. CLustering Application Randomized Search.
ANSWER: C
188. BIRCH is a ________.
A. agglomerative clustering algorithm.
B. hierarchical algorithm.
C. hierarchical-agglomerative algorithm.
D. divisive.
ANSWER: C
189. The cluster features of different subclusters are maintained in a tree called ___________.
A. CF tree.
B. FP tree.
C. FP growth tree.
D. B tree.
ANSWER: A
190. The ________ algorithm is based on the observation that the frequent sets are normally very
few in
number compared to the set of all itemsets.
A. A priori.
B. Clustering.
C. Association rule.
D. Partition.
ANSWER: D
191. The partition algorithm uses _______ scans of the databases to discover all frequent sets.
A. two.
B. four.
C. six.
D. eight.
ANSWER: A
192. The basic idea of the apriori algorithm is to generate________ item sets of a particular size &
scans
the database.
A. candidate.
B. primary.
C. secondary.
D. superkey.
ANSWER: A
193. ________is the most well known association rule algorithm and is used in most commercial
products.
A. Apriori algorithm.
B. Partition algorithm.
C. Distributed algorithm.
D. Pincer-search algorithm.
ANSWER: A
194. An algorithm called________is used to generate the candidate item sets for each pass after the
first.
A. apriori.
B. apriori-gen.
SUB : 410244(D) DMW
C. sampling.
D. partition.
ANSWER: B
195. The basic partition algorithm reduces the number of database scans to ________ & divides it
into
partitions.
A. one.
B. two.
C. three.
D. four.
ANSWER: B
196. ___________and prediction may be viewed as types of classification.
A. Decision.
B. Verification.
C. Estimation.
D. Illustration.
ANSWER: C
197. ___________can be thought of as classifying an attribute value into one of a set of possible
classes.
A. Estimation.
B. Prediction.
C. Identification.
D. Clarification.
ANSWER: B
198. Prediction can be viewed as forecasting a_________value.
A. non-continuous.
B. constant.
C. continuous.
D. variable.
ANSWER: C
199. _________data consists of sample input data as well as the classification assignment for the
data.
A. Missing.
B. Measuring.
C. Non-training.
D. Training.
ANSWER: D
200. Rule based classification algorithms generate ______ rule to perform the classification.
A. if-then.
B. while.
C. do while.
D. switch.
ANSWER: A
201. ____________ are a different paradigm for computing which draws its inspiration from
neuroscience.
A. Computer networks.
B. Neural networks.
C. Mobile networks.
D. Artificial networks.
ANSWER: B
202. The human brain consists of a network of ___________.
A. neurons.
B. cells.
SUB : 410244(D) DMW
C. Tissue.
D. muscles.
ANSWER: A
203. Each neuron is made up of a number of nerve fibres called _____________.
A. electrons.
B. molecules.
C. atoms.
D. dendrites.
ANSWER: D
204. The ___________is a long, single fibre that originates from the cell body.
A. axon.
B. neuron.
C. dendrites.
D. strands.
ANSWER: A
205. A single axon makes ___________ of synapses with other neurons.
A. ones.
B. hundreds.
C. thousands.
D. millions.
ANSWER: C
206. _____________ is a complex chemical process in neural networks.
A. Receiving process.
B. Sending process.
C. Transmission process.
D. Switching process.
ANSWER: C
207. _________ is the connectivity of the neuron that give simple devices their real power. a. b. c. d.
A. Water.
B. Air.
C. Power.
D. Fire.
ANSWER: D
208. __________ are highly simplified models of biological neurons.
A. Artificial neurons.
B. Computational neurons.
C. Biological neurons.
D. Technological neurons.
ANSWER: A
209. The biological neuron's _________ is a continuous function rather than a step function.
A. read.
B. write.
C. output.
D. input.
ANSWER: C
210. The threshold function is replaced by continuous functions called ________ functions.
A. activation.
B. deactivation.
C. dynamic.
D. standard.
ANSWER: A
211. The sigmoid function also knows as __________functions.
A. regression.
SUB : 410244(D) DMW
B. logistic.
C. probability.
D. neural.
ANSWER: B
212. MLP stands for ______________________.
A. mono layer perception.
B. many layer perception.
C. more layer perception.
D. multi layer perception.
ANSWER: D
213. In a feedforward networks, the conncetions between layers are ___________ from input to
output.
A. bidirectional.
B. unidirectional.
C. multidirectional.
D. directional.
ANSWER: B
214. The network topology is constrained to be __________________.
A. feedforward.
B. feedbackward.
C. feed free.
D. feed busy.
ANSWER: A
215. RBF stands for _____________.
A. Radial basis function.
B. Radial bio function.
C. Radial big function.
D. Radial bi function.
ANSWER: A
216. RBF have only _______________ hidden layer.
A. four.
B. three.
C. two.
D. one.
ANSWER: D
217. RBF hidden layer units have a receptive field which has a ____________; that is, a particular
input
value at which they have a maximal output.
A. top.
B. bottom.
C. centre.
D. border.
ANSWER: C
218. ___________ training may be used when a clear link between input data sets and target output
values
does not exist.
A. Competitive.
B. Perception.
C. Supervised.
D. Unsupervised.
ANSWER: D
219. ___________ employs the supervised mode of learning.
A. RBF.
SUB : 410244(D) DMW
B. MLP.
C. MLP & RBF.
D. ANN.
ANSWER: C
220. ________________ design involves deciding on their centres and the sharpness of their
Gaussians.
A. DR.
B. AND.
C. XOR.
D. RBF.
ANSWER: D
221. ___________ is the most widely applied neural network technique.
A. ABC.
B. PLM.
C. LMP.
D. MLP.
ANSWER: D
222. SOM is an acronym of _______________.
A. self-organizing map.
B. self origin map.
C. single organizing map.
D. simple origin map.
ANSWER: A
223. ____________ is one of the most popular models in the unsupervised framework.
A. SOM.
B. SAM.
C. OSM.
D. MSO.
ANSWER: A
224. The actual amount of reduction at each learning step may be guided by _________.
A. learning cost.
B. learning level.
C. learning rate.
D. learning time.
ANSWER: C
225. The SOM was a neural network model developed by ________.
A. Simon King.
B. Teuvokohonen.
C. Tomoki Toda.
D. Julia.
ANSWER: B
226. SOM was developed during ____________.
A. 1970-80.
B. 1980-90.
C. 1990 -60.
D. 1979 -82.
ANSWER: D
227. Investment analysis used in neural networks is to predict the movement of _________ from
previous
data.
A. engines.
B. stock.
C. patterns.
SUB : 410244(D) DMW
D. models.
ANSWER: B
228. SOMs are used to cluster a specific _____________ dataset containing information about the
patient's
drugs etc.
A. physical.
B. logical.
C. medical.
D. technical.
ANSWER: C
229. GA stands for _______________.
A. Genetic algorithm
B. Gene algorithm.
C. General algorithm.
D. Geo algorithm.
ANSWER: A
230. GA was introduced in the year __________.
A. 1955.
B. 1965.
C. 1975.
D. 1985.
ANSWER: C
231. Genetic algorithms are search algorithms based on the mechanics of natural_______.
A. systems.
B. genetics.
C. logistics.
D. statistics.
ANSWER: B
232. GAs were developed in the early _____________.
A. 1970.
B. 1960.
C. 1950.
D. 1940.
ANSWER: A
233. The RSES system was developed in ___________.
A. Poland.
B. Italy.
C. England.
D. America.
ANSWER: A
234. Crossover is used to _______.
A. recombine the population's genetic material.
B. introduce new genetic structures in the population.
C. to modify the population's genetic material.
ANSWER: A
235. The mutation operator ______.
ANSWER: B
236. Which of the following is an operation in genetic algorithm?
SUB : 410244(D) DMW
A. Inversion.
B. Dominance.
C. Genetic edge recombination.
ANSWER: D
237. . ___________ is a system created for rule induction.
A. RBS.
B. CBS.
C. DBS.
D. LERS.
ANSWER: D
238. NLP stands for _________.
A. Non Language Process.
B. Nature Level Program.
C. Natural Language Page.
D. Natural Language Processing.
ANSWER: D
239. Web content mining describes the discovery of useful information from the _______contents.
A. text.
B. web.
C. page.
D. level.
ANSWER: B
240. Research on mining multi-types of data is termed as _______ data.
A. graphics.
B. multimedia.
C. meta.
D. digital.
ANSWER: B
241. _______ mining is concerned with discovering the model underlying the link structures of the
web.
A. Data structure.
B. Web structure.
C. Text structure.
D. Image structure.
ANSWER: B
242. _________ is the way of studying the web link structure.
A. Computer network.
B. Physical network.
C. Social network.
D. Logical network.
ANSWER: C
243. The ________ propose a measure of standing a node based on path counting.
A. open web.
B. close web.
C. link web.
D. hidden web.
ANSWER: B
244. In web mining, _______ is used to find natural groupings of users, pages, etc.
A. clustering.
B. associations.
C. sequential analysis.
D. classification.
SUB : 410244(D) DMW
ANSWER: A
245. In web mining, _________ is used to know the order in which URLs tend to be accessed.
A. clustering.
B. associations.
D. classification.
ANSWER: C
246. In web mining, _________ is used to know which URLs tend to be requested together.
A. clustering.
B. associations.
D. classification.
ANSWER: B
247. __________ describes the discovery of useful information from the web contents.
A. Web content mining.
B. Web structure mining.
C. Web usage mining.
ANSWER: A
248. _______ is concerned with discovering the model underlying the link structures of the web.
ANSWER: B
249. The ___________ engine for a data warehouse supports query-triggered usage of data
A. NNTP
B. SMTP
C. OLAP
D. POP
ANSWER: C
250. ________ displays of data such as maps, charts and other graphical representation allow data
to be
presented compactly to the users.
A. Hidden
B. Visual
C. Obscured
D. Concealed
ANSWER: B
ZEAL EDUCATION SOCIETY’S
ZEAL COLLEGE OF ENGINEERING AND RESEARCH
NARHE │PUNE -41 │ INDIA
DEPARTMENT OF COMPUTER ENGINEERING
Name of the Teacher: V. R. Vasekar
Class: BE Subject: Data Mining and Warehousing

AY: 2020-21 SEM: I
UNIT-1
1) Binary attribute are
a) This takes only two values. In general, these values will be 0 and 1 and
.they can be coded as one bit
b) The natural environment of a certain species
c) Systems that can be used without knowledge of internal operations
d) None of these
Ans: a
Explanation: All statement are true about Machine Learning.
2) “Efficiency and scalability of data mining algorithms” issues come under?
a) Mining Methodology and User Interaction Issues
b) Performance Issues
c) Diverse Data Types Issues
d) None of the above
Ans: b
Explanation: In order to effectively extract the information from huge amount of data
in databases, data mining algorithm must be efficient and scalable.
3) ——- is not a data mining functionality?
a) Clustering and Analysis
b) Selection and interpretation
c) Classification and regression
Characterization and Discrimination
Ans: b
Explanation: Selection and interpretation
4) ——– is the output of KDD

a) Query
b) Data
c) Useful Information
d) information
Ans: c
Explanation: Useful Information
5) Which of the following is not belong to data mining?t is unsupervised

learning ?
a) Knowledge extraction
b) Data archaeology
c) Data exploration
d) Data transformation
Ans: d
Explanation: Data transformation
6) Which of the following is the right approach to Data Mining?
e) Infrastructure, exploration, analysis, exploitation, interpretation
f) Infrastructure, exploration, analysis, interpretation, exploitation
g) Infrastructure, analysis, exploration, interpretation, exploitation
None of these
Ans: b
Explanation: Infrastructure, exploration, analysis, interpretation, exploitation
7) Background knowledge referred to

a) Additional acquaintance used by a learning algorithm to facilitate the
learning process
b) A neural network that makes use of a hidden layer
c) It is a form of automatic learning.
d) None of these
Ans: a
Explanation: Additional acquaintance used by a learning algorithm to facilitate the learning
process
8)
Data mining is
a) The actual discovery phase of a knowledge discovery process
b) The stage of selecting the right data for a KDD process
c) A subject-oriented integrated time variant non-volatile collection of
data in support of management
d) None of these
Ans: a
Explanation: The actual discovery phase of a knowledge discovery process
09)
Data selection is
a) The actual discovery phase of a knowledge discovery process

b) The stage of selecting the right data for a KDD process
c) A subject-oriented integrated time variant non-volatile collection of
data in support of management
d) None of these
Ans: b
Explanation: The stage of selecting the right data for a KDD process
10) The Example of nominal attribute is
a) Hair_color
b) smoker
c) temperature
d) drink size
Ans: a
Explanation: Nominal means “relating to names.” The values of a nominal attribute are
symbols or names of things
11) The Example of binary attribute is
a) gender
b) drink_size
c) tempertaure
d) professionl_rank
Ans b
Explanation: A binary attribute is a nominal attribute with only two categories or states:0
or1
12) The Example of ordinary attribute is
a) Years_of_experience
b) age
c) occupation
d) customer_id
Ans: b
An ordinal attribute is an attribute with possible values that have a meaningful
Explanation: order or ranking among them
13) Data cleaning includes____
a. Handling missing values and noisy data
b. Reduction of attributes
c. Relevant attribute selection
d. Sample data selection
Ans: a
Explanation: Data cleaning (or data cleansing) routines attempt to fill in missing values,
smooth out noise while identifying outliers, and correct inconsistencies in the
data.
14) To deal with missing values, the following strategy is used__
e. Use a measure of central tendency
f. Reduction of attribute
g. Sample data selection
h. Data converted into other form
Ans: a
Explanation: measures of central tendency, which indicate the “middle” value of a data
distribution
15) Noise is ___
a) Missing value from dataset
b) Inaccurate data
c) a random error or variance in a measured variable
d) the data whose value known to user
Ans: c
Explanation:
16) At the time of data integration following problem ocuures___

a) Selection of proper values
b) Raw data conversion
c) Entity identification
d) Attribute subset selction
Ans: c
Explanation: Schema integration and object matching can be tricky.
17) Which of the following is not example of data reduction strategy?
a) Outlier detection
b) Principal Component Analysis
c) Attribute subset selection
d) Wavelet transforms
Ans: a
Explanation: Outlier detection
18) Data Transformation Strategies includes____

a) smoothing
b) Attribute construction
c) Normalization
d) All of the above
Ans: d
Explanation: Smoothing, attribute construction and normalization includes in data
transformation
19) Data Discretization is used for____
a) transforms numeric data by mapping values to interval or concept

labels
b) smoothing
c) Attribute construction
d) Normalization
Ans: a
Explanation: transforms numeric data by mapping values to interval or concept labels
20) KDD stands for
a) K data values
b) Knowledge discovery from dataset
c) K dataset
Ans. b
Explaination Knowledge discovery from dataset
21)
Data transformation includes:
a) data are transformed and consolidated into forms appropriate for

mining by performing summary or aggregation operations
b) an essential process where intelligent methods are applied to extract
data patterns
c) data relevant to the analysis task are retrieved from the database
d) it is used for knowledge representation.
Ans a
Explanation data are transformed and consolidated into forms appropriate for mining by
performing summary or aggregation operations
22) Pattern evaluation includes__

data patterns
c) data relevant to the analysis task are retrieved from the database
d) Identify the truly interesting patterns representing knowledge based on
interestingness measures
Ans d
Explanation To identify the truly interesting patterns representing knowledge based on
23) In KDD, the knowledge representation term used for__

data patterns
c) visualization and knowledge representation techniques are used to
present mined knowledge to users
d) Identify the truly interesting patterns representing knowledge based on
Ans c
Explanation visualization and knowledge representation techniques are used to present
mined knowledge to users
24) Data mining functionalities are used to___
a) to specify the kinds of patterns or knowledge to be found in data
mining tasks
b) to select data
c) to find missing values
d) to analyze the mining result
Ans a
Explanation a) Data mining functionalities are used to specify the kinds of patterns or
knowledge to be found in data mining tasks
25) The challenging issues in data mining research____

a) efficiency and scalability
b) dealing with diverse data types
c) user interaction
d) all of the above
Ans d
Explanation There are many challenging issues in data mining research. Areas include
mining methodology, user interaction, efficiency and scalability, and dealing
with diverse data types. Data mining research has strongly impacted society
and will continue to do so in the future
Name and Sign of Subject Teacher

Name of the Teacher: V. R. Vasekar
Class: BE Subject: Data Mining and Warehousing

AY: 2020-21 SEM: II
UNIT-2 Data Warehouse

1. ___ is a subject oriented, integrated, time variant, non-volatile collection of data in
support of management decisions.
a) Data Mining
b) Data Warehousing
c) Web mining
d) Text mining
Ans: b
Explanation: Data Warehousing
2. Data Warehouse is
a) Read only
b) Write only
c) Read and write only
d) none
Ans: a
Explanation: Because of historical data storage
3. Expansion for DSS in DW is___
a) Decision Single System
b) Decision storable system
c) Decision Support System
d) Data Support System
Ans: c
Explanation: Decision support system
4. The important aspect of data warehouse environment is that data found within the
data warehouse is___
a) Subject oriented
b) Time-variant
c) Integrated
d) All of the above
Ans: d
Explanation: All are correct
5. The time horizon in Data warehouse is usually__
a) 1-2 year
b) 3-4 year
c) 5-6 years
d) 5-10 years
Ans: d
Explanation: 5 to 10 years
6. The data is stored , retrieved and updated in___
a) OLAP
b) OLTP
c) SMTP
d) FTP
Ans: b
Explanation: Online Analytical Transaction processing
7. ___describes the data oriented in the data warehouse
a) Relational data
b) Operational data
c) Metadata
d) Informational data
Ans: c
Explanation: metadata
8. ___ predicts the future trends and behaviours, allowing business managers to make
proactive knowledge-driven decisions
a) Data warehouse
b) Data mining
c) Datamarts
d) metadata
Ans: b
Explanation:
9. ___ is the heart of Datawarehouse

a) Data mining database server
b) Data warehouse database servers
c) Data mart database servers
d) Relational database servers
Ans: b
Explanation: Data warehouse database servers
10. ___is the specialized data warehouse database

a) Oracle
b) DBZ
c) Informix
d) Redbricks
Ans: d
Explanation: Redbricks
11.---defines the structure of the data held in operational databases and used by operational
applications
a) User-level metadata
b) Data warehouse metadata
c) Operational metadata
d) Data mining metadata
Ans c
Explanation: Operational metadata
12.----helds the catelog of the warehouse database system

a) Application level metadata
b) Algorithmic level metadata
c) Departmental level metadata
d) Core warehouse metadata
Ans: b
Algorithmic level metadata
Explanation:
13. ___maps the core warehouse metadata to business concepts, familiar and useful to end-
users
a) Application level metadata.
b) User level metadata.C.
c) Enduser level metadata.
d) Core level metadata
Ans: a
Explanation:
a) One
b) Two
c) Three
d) four
Ans: a
Explanation: Only one fact table
15. The source of all data warehouse data is the__
a) operational environment
b) informal environment
c) formal environment.
d) technology environmen
Ans: a
Explanation:
16.The @active data warehouse architecture includes which of the following?
a) At least one data mart
b) Data that can extracted from numerous internal and external sources
c) Near real-time updates
d) All of the above.
Ans: d
Explanation:
17.An operational system is which of the following?

a) A system that is used to run the business in real time and is based
on historical data.
b) A system that is used to run the business in real time and is based
on current data.
c) A system that is used to support decision making and is based on
current data.
d) A system that is used to support decision making and is based on
historical data.
Ans: b
Explanation:
18.A data warehouse is which of the following?

a) Can be updated by end users.
b) Contains numerous naming conventions and formats.
c) Organized around important subject areas
d) Contains only current data.
Ans: c
Explanation: Data warehouse is subject oriented
19. Good performance can be achieved in a data mart environment by extensive use of
a) Indexes
b) creating profile records
c) volumes of data
d) all of the above
Ans: d
Explanation:
20. Warehouse administrator responsible for
a) Administrator
b) Maintenance
c) both a and b
d) none of the above
Ans c
Explaination
21. What is data cube?
a) allows data to be modeled and viewed in multiple dimensions
b) data with dimensions
c) data values
d) description about data
Ans. a
23 .Which of the following is not a multidimensional data model?
a) Star schema
b) Fact constellation
c) Snowflake schemas
d) Entity-relationship model
Ans d
Explanation Three models of data warehouse: star, snowflake and fact constellation
24. Snowflake schema consists of ___fact tables
a) One
b) Two
c) Three
d) four
Ans a
Explanation Having only one fact table and many dimension tables
25.Fact constellation consists of __ fact tables
a) one
b) two
c) three
d) many
Ans d
Explanation Many fact tables and many dimension tables
Name and Sign of Subject Teacher

1. ...................... is an essential process where intelligent methods are applied
to extract data patterns.
A) Data warehousing
B) Data mining
C) Text mining
D) Data selection
2. Data mining can also applied to other forms such as ................
i) Data streams
ii) Sequence data
iii) Networked data
iv) Text data
v) Spatial data
A) i, ii, iii and v only
B) ii, iii, iv and v only
C) i, iii, iv and v only
D) All i, ii, iii, iv and v
3. Which of the following is not a data mining functionality?
A) Characterization and Discrimination
B) Classification and regression
C) Selection and interpretation
D) Clustering and Analysis
4. ............................. is a summarization of the general characteristics or

features of a target class of data.
A) Data Characterization
B) Data Classification
C) Data discrimination
D) Data selection
5. ............................. is a comparison of the general features of the target
class data objects against the general features of objects from one or
multiple contrasting classes.
D) Data selection
6. Strategic value of data mining is ......................
A) cost-sensitive
B) work-sensitive
C) time-sensitive
D) technical-sensitive
7. ............................. is the process of finding a model that describes and

distinguishes data classes or concepts.
D) Data selection
8. The various aspects of data mining methodologies is/are ...................
i) Mining various and new kinds of knowledge
ii) Mining knowledge in multidimensional space
iii) Pattern evaluation and pattern or constraint-guided mining.
iv) Handling uncertainty, noise, or incompleteness of data
A) i, ii and iv only
B) ii, iii and iv only
C) i, ii and iii only
D) All i, ii, iii and iv
9. The full form of KDD is ..................
A) Knowledge Database
B) Knowledge Discovery Database
C) Knowledge Data House
D) Knowledge Data Definition

10. The out put of KDD is .............
A) Data
B) Information
C) Query
D) Useful information
Data Warhouse & Data Mining 700 - MCQ’s
TOPIC ONE – INTRODUCTION TO DATA MINING

EASY QUESTIONS
1.Data mining is an integral part of _________.

A. SE.
B. DBMS.
C. KDD.
D. OS.
ANSWER: C
2. __________ is a subject-oriented, integrated, time-variant, non-volatile collection of data in

support of management decisions.
A. Data Mining.
C. Web Mining.
D. Text Mining.
ANSWER: B
3. KDD describes the _________.

A. whole process of extraction of knowledge from data
B. extraction of data
C. extraction of information
D. extraction of rules
ANSWER: A

A. read only.
B. write only.
C. read write only.
D. none.
ANSWER: A

ANSWER: A
warehouse is___________.
B. time-variant.
C. integrated.
ANSWER: D
1
A. OLAP.
B. OLTP.
C. SMTP.
D. FTP.
ANSWER: B

A. Relational data.
C. Metadata.
ANSWER: C
9. ____________predicts future trends &behaviors, allowing business managers to make

proactive,knowledge-driven decisions.
A. Data warehouse.
B. Data mining.
C. Datamarts.
D. Metadata.
ANSWER: B

ANSWER: B
11. ________________defines the structure of the data held in operational databases and used
byoperational applications.
ANSWER: C

ANSWER: B
users.
ANSWER: A
2
A. data warehouse.
B. data mining.
C. operational.
D. informational.
ANSWER: C

A. OLTP
B. files
C. RDBMS
D. data warehouse
ANSWER: D

A. monoatomic data.
B. diatomic data.
C. atomic data.
ANSWER: C

ANSWER: C

A. Metadata.
B. Microdata.
C. Minidata.
D. Multidata.
ANSWER: A

B. Repository.
D. Data dictionary.
ANSWER: C
B. deduplication.
C. disambiguation.
D. segmentation.
ANSWER: D

A. retrospective.
B. interrogative.
C. predictive.
D. imperative.
3
ANSWER: C

A. Association.
B. Preferencing.
C. Segmentation.
D. Classification.
ANSWER: B

A. exception.
B. alerts.
C. errors.
D. bugs.
ANSWER: B

ANSWER: B

A. recovery.
B. data cleaning.
C. data cleansing.
D. data pruning.
ANSWER: B
system.
C. Data dictionary.
D. Database.
ANSWER: B

A. segmentation.
B. visualization.
C. correction.
D. association.
ANSWER: D
ANSWER: B
4
C. Metadata.
ANSWER: C
30. Which of the following is not an old detail storage medium?

B. RAID.
C. Microfinche.
D. Pen drive.
ANSWER: D

A. entities.
B. facts.
C. keys.
ANSWER: B
32. Which of the following is not the other name of Data mining?
D. Data integration.
ANSWER: D

A. Clustering.
B. Regression.
C. Summarization.
ANSWER: B

A. Classification.
B. Regression.
ANSWER: C

A. Descriptive.
B. Predictive.
C. Regression.
ANSWER: A

A. current data.
B. historical data.
D. assumptions.
5
ANSWER: B

A. Regression.
C. Prediction.
D. Classification.
ANSWER: D
A. Regression.
C. Prediction.
D. Classification.
ANSWER: B

A. Regression.
D. Prediction.
ANSWER: B

B. Summarization.
C. Clustering.
D. Prediction.
ANSWER: C
41. _________ is the input to KDD.

A. Data.
B. Information.
C. Query.
D. Process.
ANSWER: A

A. Data.
B. Information.
C. Query.
ANSWER: D

A. three.
B. four.
C. five.
D. six.
ANSWER: C
6
A. selection.
B. preprocessing.
C. transformation.
D. interpretation.
ANSWER: B
45. Converting data from different sources into a common format for processing is called as
________.
A. selection.
B. preprocessing.
C. transformation.
D. interpretation.
ANSWER: C

A. selection.
B. transformaion.
C. data mining.
D. interpretation.
ANSWER: D

A. outliers.
B. rare values.
D. Inliers
ANSWER: A

A. Graphical.
B. Geometric.
C. Icon-based.
D. Pixel-based.
ANSWER: B
A. Induction.
B. Compression.
C. Approximation.
D. Substitution.
ANSWER: A
50. Describing some characteristics of a set of data by a general model is viewed as

A. Induction.
B. Compression.
C. Approximation.
D. Summarization.
ANSWER: B

A. Induction.
B. Compression.
C. Approximation.
7
D. Summarization.
ANSWER: C

A. changing data.
B. noisy data.
C. outliers.
D. missing data.
ANSWER: B
confidential.
A. authorized use.
ANSWER: B
A. Preprocessed.
B. Cleaned.
C. Real-world.
D. Transformed.
ANSWER: C
D. Web development.
ANSWER: A
D. Web development.
ANSWER: B
57. A _____ algorithm takes all the data at once and tries to create a hypothesis based on this data.
A. supervised.
B. batch learning.
C. unsupervised.
D. incremental learning.
ANSWER: B
58. A ________ algorithm takes a new piece of information at each learning cycle and tries to revise
the theory using
new data.
A. supervised.
B. batch learning.
C. unsupervised.
D. incremental learning.
ANSWER: B
8
59. ________ is used to find the vaguely known data.
A. SQL.
B. KDD.
C. Data mining.
D. Sybase.
ANSWER: C
60. The easiest way to gain access to the data and facilitate effective decision making is to set up a
_______.
A. database.
B. data mart.
C. data warehouse.
D. operational.
ANSWER: C
61. Smaller local data warehouse is called as ____.

A. data mart.
B. database.
C. data model.
D. meta data.
ANSWER: B
62. The _______ data are stored in data warehouse.

A. operational.
B. historical.
C. transactional.
D. optimized.
ANSWER: B
63. A decision support system is a system that ________.

A. can constantly change over time.
B. cannot change.
C. copies the data.
D. supports the system.
ANSWER: A
64. Metadata is used by the end users for ______.

A. managing database.
B. structuring database.
C. querying purposes.
D. making decisions.
ANSWER: C
65. The _________ techniques are used to load information from operational database to data
warehouse.
A. reengineering.
B. reverse.
C. transfer.
D. replication.
ANSWER: D
9
66. In machine learning ________ phase try to find the patterns from observations.
A. observation
B. theory
C. analysis
D. prediction
ANSWER: C
67. Information content is closely related to ______ and transparency.

A. algorithm.
B. search space.
C. learning.
D. statistical significance.
ANSWER: D
68. The ________ is used to express the hypothesis describing the concept.
A. computer language.
B. algorithm.
C. definition.
D. theory
ANSWER: A
69. A definition of a concept is complete if it recognizes _________.

A. all the information.
B. all the instances of a concept.
C. only positive examples.
D. negative examples.
ANSWER: B
70. The results of machine learning algorithms are always have to be checked for their _________.
A. observations.
B. calculations
C. programs.
D. statistical relevance.
ANSWER: D
71. A ________ is necessary condition for KDDs effective implement.

A. data set.
B. database.
C. data warehouse.
D. data.
ANSWER: C
72. KDD is a ________.

A. new technology that is use to store data.
B. multidisciplinary field of research.
C. database technology.
D. expert system.
ANSWER: B
10
INTERMEDIATE QUESTIONS

ANSWER: C

ANSWER: B

eliminated.
eliminated.
ANSWER: A

ANSWER: B

ANSWER: A

ANSWER: A
79. Business Intelligence and data warehousing is not used for ________.
A. Forecasting.
B. Data Mining.
D. Discarding data.
ANSWER: D
11
A. root node.
B. decision tree.
C. siblings.
D. branches.
ANSWER: B
81. Reducing the number of attributes to solve the high dimensionality problem is called as
________.
C. cleaning.
D. Overfitting.
ANSWER: B
A. missing data.
B. changing data.
C. irrelevant data.
D. noisy data.
ANSWER: C

A. inventory finalisation.
B. sales.
C. marketing products.
D. Debt collection.
ANSWER: A
ANSWER: D
A. border set.
B. frequent set.
D. lattice.
ANSWER: B
86. Metadata describes __________.

A. contents of database.
B. structure of contents of database.
C. structure of database.
D. database itself.
ANSWER: B
87. The partition of overall data warehouse is _______.

A. database.
B. data cube.
C. data mart.
12
D. operational data.
ANSWER: C
88. The information on two attributes is displayed in ____________ in scatter diagram.

A. visualization space.
B. scatter space.
C. cartesian space.
D. interactive space.
ANSWER: C
89. OLAP is used to explore the ___________ knowledge.

A. shallow.
B. deep.
C. multidimensional.
D. hidden.
ANSWER: C
90. Hidden knowledge can be found by using ________.

A. searching algorithm.
B. pattern recognition algorithm.
C. searching algorithm.
D. clues.
ANSWER: B
91. The next stage to data selection in KDD process ______.

A. enrichment.
B. coding.
C. cleaning.
D. reporting.
ANSWER: C
92. Enrichment means ____.

A. adding external data.
B. deleting data.
C. cleaning data.
D. selecting the data.
ANSWER: A
93. The decision support system is used only for _______.

A. cleaning.
B. coding.
C. selecting.
D. queries.
ANSWER: D
94. Which of the following is closely related to statistical significance and transparency?
A. Classification Accuracy.
B. Transparency.
C. Statistical significance.
D. Search Complexity.
ANSWER: B
13
95. ________ is the technique which is used for discovering patterns in dataset at the beginning of
data mining process.
A. Kohenon map.
B. Visualization.
C. OLAP.
D. SQL.
ANSWER: B
96. _______ is the heart of knowledge discovery in database process.

A. Selection.
B. Data ware house.
C. Data mining.
D. Creative coding.
ANSWER: D
97. In KDD and data mining, noise is referred to as ________.

A. repeated data.
B. complex data.
C. meta data.
D. random errors in database.
ANSWER: D
98. The technique of learning by generalizing from examples is ________.

A. incremental learning.
B. inductive learning.
C. hybrid learning.
D. generalized learning.
ANSWER: B
99. The _______ plays an important role in artificial intelligence.

A. programming skill.
B. scheduling.
C. planning.
D. learning capabilities.
ANSWER: D
100. Data mining is used to refer ______ stage in knowledge discovery in database.
A. selection.
B. retrieving.
C. discovery.
D. coding.
ANSWER: C
101. ______ could generate rule automatically.

A. KDD.
B. machine learning.
C. artificial intelligence.
D. expert system.
ANSWER: B
102. A good introduction to machine learning is the idea of ______.

A. concept learning.
B. content learning.
C. theory of falsification.
14
D. Poppers law.
ANSWER: A
103. The algorithms that are controlled by human during their execution is _______ algorithm.
A. unsupervised.
B. supervised.
C. batch learning.
D. incremental.
ANSWER: B
104. Background knowledge depends on the form of ______________.

A. theoretical knowledge.
B. hypothesis.
C. formulae.
D. knowledge representation.
ANSWER: D
ADVANCED QUESTIONS
ANSWER: B
D. access to data.
ANSWER: C
107. Multidimensional database is otherwise known as____________.

A. RDBMS
B. DBMS
C. EXTENDED RDBMS
D. EXTENDED DBMS
ANSWER: B
108. __________ are designed to overcome any limitations placed on the warehouse by the nature
of therelational data model.
D. Data repository.
ANSWER: C
B. border set.
C. lattice.
D. infrequent sets.
15
ANSWER: A
B. Classification.
C. Clustering.
ANSWER: C
A. if-then.
B. while.
C. do while.
D. switch.
ANSWER: A
valuesdoes not exist.
A. Competitive.
B. Perception.
C. Supervised.
D. Unsupervised.
ANSWER: D
A. text.
B. web.
C. page.
D. level.
ANSWER: B

A. graphics.
B. multimedia.
C. meta.
D. digital.
ANSWER: B

C. Social network.
D. Logical network.
ANSWER: C
A. clustering.
B. associations.
D. classification.
ANSWER: A
16
A. clustering.
B. associations.
D. classification.
ANSWER: B
118. The ___________ engine for a data warehouse supports query-triggered usage of data
A. NNTP
B. SMTP
C. OLAP
D. POP
ANSWER: C
119. ________ displays of data such as maps, charts and other graphical representation allow data
to be presented compactly to the users.
A. Hidden
B. Visual
C. Obscured
D. Concealed
ANSWER: B
120. Which of the following are the important qualities of good learning algorithm.
A. Consistent, Complete.
B. Information content, Complex.
C. Complete, Complex.
D. Transparent, Complex.
ANSWER: A
TOPIC TWO – GETTING TO KNOW YOUR DATA

EASY QUESTIONS
121. The _______ is a symbolic representation of facts or ideas from which information can
potentially be extracted.
A. knowledge.
B. data.
C. algorithm.
D. program.
ANSWER: B
122. A collection of interesting and useful patterns in database is called _______.

A. knowledge.
B. information.
C. data.
D. algorithm.
ANSWER: A
D. access to data.
ANSWER: C
17
124. The process of finding the right formal representing of a certain body of knowledge in order to
represent it inknowledge based system is__________.
A. re-engineering.
B. replication.
C. knowledge engineering.
D. reverse engineering.
ANSWER: C
125. OR methods deals with _______type of data.

A. quantitative.
B. qualitative.
C. standard.
D. predict.
ANSWER: A
126. ________analysis divides data into groups that are meaningful, useful, or both.
A. Cluster.
B. Association.
C. Classifiction.
D. Relation.
ANSWER: A
127. A representation of data objects as columns and attributes as rows is called_________.

A. matrix.
B. data matrix.
C. table.
D. file.
ANSWER: B
128. Which of the following is not a data mining attribute?

A. nominal.
B. ordinal.
C. interval.
D. multiple.
ANSWER: D
129. Patterns of machine-language program are_________.

A. definitive theories.
B. hypothesis.
C. not-definitive theories.
D. quantitative.
ANSWER: B
130. Nominal and ordinal attributes are collectively referred to as_________ attributes.
A. qualitative.
B. perfect.
C. consistent.
D. optimized.
ANSWER: A
131. A data set can often be viewed as a collection of ______.

A. data mart.
B. data.
18
C. data object.
D. template.
ANSWER: C
132. An important element in machine learning is ________.

A. flow.
B. knowledge.
C. observation.
D. language.
ANSWER: C
133. _______ is the closeness of repeated measurements to one another.

A. Precision.
B. Bias.
C. Accuracy.
D. non-scientific.
ANSWER: A
ANSWER: B
134. Which of the following is not a data mining attribute?

A. nominal.
B. ordinal.
C. interval.
D. multiple.
ANSWER: D
135. Patterns of machine-language program are_________.

A. definitive theories.
B. hypothesis.
C. not-definitive theories.
D. quantitative.
ANSWER: B
136. Nominal and ordinal attributes are collectively referred to as_________ attributes.
A. qualitative.
B. perfect.
C. consistent.
D. optimized.
ANSWER: A
137. A data set can often be viewed as a collection of ______.

A. data mart.
B. data.
C. data object.
D. template.
ANSWER: C
138. An important element in machine learning is ________.

A. flow.
B. knowledge.
C. observation.
D. language.
ANSWER: C
19
139. ___________ is used for discrete target variable.
A. Nominal.
B. Classification.
C. Clustering.
D. Association.
ANSWER: B
140. A goal of data mining includes which of the following?

A. To explain some observed event or condition
B. To confirm that data exists
C. To analyze data for expected relationships
D. To create a new data warehouse
ANSWER: A
141. is a subject-oriented, integrated, time-variant, nonvolatile collection of data in supportof

management decisions.
A. Data Mining.
C. Web Mining.
D. Text Mining.
ANSWER: B
142. Collection, analysis, interpretation or explanation of data.

A. Statistics
B. Information retrieval
C. Data mining
D. Cluster analysis
Answer: A
143. Data objects represesents

A. Values
B. Entity
C. Data
D. Attributes
Answer : B
INTERMEDIATE QUESTIONS
A. domain consistance.
B. de-duplication.
C. disambiguation.
D. segmentation.
ANSWER: D
The _____ is a useful method of discovering patterns at the beginning of data mining process.
A. calculating distance.
B. visualization techniques.
C. decision trees.
D. association rules.
ANSWER: B
20
145. Data mining methodology states that in optimal situation data mining is an _____.
A. standard process.
B. complete process.
C. creative process.
D. ongoing process.
ANSWER: D
146. ___________ is a knowledge discovery process.

A. Data cleaning.
B. Data warehousing.
C. Data mining.
D. Data transformation.
ANSWER: A
147. OLAP is used for __________.

A. online application processing.
B. online analytical processing.
C. online aptitude processing.
D. online administration and processing.
ANSWER: B
148. Which of the following is not an issue related to concept learning

A. Supervised learning.
B. Unsupervised learning.
C. Self learning.
D. Concept learning.
ANSWER: D
149. Removing duplicate records is a process called________.

A. recovery.
B. data cleaning.
C. data cleansing.
D. data pruning.
ANSWER: B
150. Data marts that incorporate data mining tools to extract sets of data is called______.
ANSWER: B
151. The problem of finding hidden structure in unlabelled data is called…

A. Supervised learning
B. Unsupervised learning
C. Reinforcement learning
D. Semisupervised learning
ANSWER : B
152. Task of inferring a model from labelled training data is called

21
D. Semisupervised learning
ANSWER : B
153. Self-organizing maps are an example of…

D. Missing data imputation
ANSWER : A
154. The time horizon in Data warehouse is usually

A. 1-2 years.
B. 3-4years.
C. 5-6 years.
D. 5-10 years.
ANSWER: D
155. Classification rules are extracted from

A. root node
B. decision tree.
C. siblings.
D. branches.
ANSWER: B
156. Which one of the following is not a part of empirical cycle in scientific research?
A. Observation
B. Theory.
C. Self learning.
D. Prediction.
ANSWER: C
157. In machine learning ________ phase try to find the patterns from observations.
A. observation
B. theory
C. analysis
D. prediction
ANSWER: C
158. ANSWER: D
Data warehouse architecture is based on ______________.
A. DBMS.
B. RDBMS.
C. Sybase.
D. SQL Server.
ANSWER: B
ADVANCED QUESTIONS
159. The ___ algorithm can be applied in cleaning data.

A. search.
B. pattern recognition.
C. learning.
D. clustering.
ANSWER: B
22
160. ________ is the type of pollution that is difficult to trace.
A. Duplication of records.
B. Ambiguition.
C. Lack of domain consistency.
D. Lack of information.
ANSWER: C
161. The statement that is true about data mining is ______.

A. data mining is not a single technique.
B. it finds the hidden patterns from data set.
C. it is a real discovery process.
D. all forms of pollutions are found during the data mining stage itself.
ANSWER: D
162. The first step in data mining project is ________.

A. rough analysis of data set using traditional query tools.
B. cleaning the data.
C. recognizing the patterns.
D. visualizing the patterns.
ANSWER: A
163. SQL can find ________ type of data.

A. narrow data.
B. multidimensional data.
C. shallow data.
D. hidden data.
ANSWER: C
164. _______ is used to find relationship between multidimensional data.

A. K-nearest neighbor.
B. Decision trees.
C. Association rules.
D. OLAP tools.
ANSWER: D
165. Which one of the following is not true about OLAP?

A. They create no new knowledge.
B. OLAP is powerful that data mining tool.
C. They cannot search for new solution.
D. OLAP tool store their data in special multidimensional format.
ANSWER: B
166. Genetic algorithm is viewed as a kind of______.

A. meta learning strategy.
B. machine learning.
C. evolution.
D. OLAP tool.
ANSWER: A
167. The _________is a knowledge that can be found by using pattern recognition algorithm.
A. hidden knowledge.
B. deep.
C. shallow.
23
D. multidimensional.
ANSWER: A
168. Shannons notation of information content of message is_______.

A. Log 1divided by n equals log n.
B. log n equals log 1divided by n.
C. log 1divided by n equals minus log n.
D. log minus n =log 1divided by n.
ANSWER: C
169. Which of the following features usually applies to data in a data warehouse
A. Data are often deleted.
B. Most applications consist of transactions.
C. Data are rarely deleted.
D. Relatively few records are processed by applications.
ANSWER: C
170. Which of the following is true

A. The data warehouse consists of data marts and operational data
B. The Data Warehouse consists of data marts and application data.
C. The Data Warehouse is used as a source for the operational data.
D. The operational data are used as a source for the data warehouse
ANSWER: D
171. How do you better define a data warehouse as

A. Can be updated by end users.
B. Contains numerous naming conventions and formats.
C. Organized around important subject areas.
D. Contains only current data.
ANSWER: C
172. Which of the following is an operational system

A. A system that is used to run the business in real time and is based on historical data
B. A system that is used to run the business in real time and is based on current data.
C. A system that is used to support decision making and is based on current data.
D. A system that is used to support decision making and is based on historical data.
ANSWER: B
173. The generic two-level data warehouse architecture includes _______________.

C. near off-time updates.
D. historic data.
ANSWER: B
174. Which of the following is reconciled data

A. Current data intended to be the single source for all decision support systems
B. Data stored in the various operational systems throughout the organization.
C. Data stored in one operational system in the organization.
D. Data that has been selected and formatted for end-user support applications.
ANSWER: A
24
175. Which of the following is an extract process
A. Capturing all of the data contained in various operational systems.
B. Capturing a subset of the data contained in various operational systems.
C. Capturing all of the data contained in various decision support systems.
D. Capturing a subset of the data contained in various decision support systems.
ANSWER: B
176. Which of the following is the not a types of clustering?

A. K-means.
B. Hiearachical.
C. Partitional.
D. Splitting.
ANSWER: D
177. Data Transformation includes____________.

ANSWER: A
178. The _____________ is called a multi field transformation.

A. conversion of data from one field into multiple fields.
B. conversion of data from fields into field.
C. conversion of data from double fields into multiple fields
D. conversion of data from one field to one field.
ANSWER: A
179. Which of the given technology is not well-suited for data mining
A. Expert system technology.
B. Data visualization.
C. Technology limited to specific data types such as numeric data types.
D. Parallel architecture.
ANSWER: C
180. What is true about the multidimensional model?

A. It typically requires less disk storage.
B. It typically requires more disk storage.
C. Typical business queries requiring aggregate functions take more time.
D. Typical business queries requiring aggregate functions take more time.
ANSWER: B
181. Which of the following function involves data cleaning, data standardizing and summarizing
A. Storing data.
B. Transforming data.
C. Data acquisition.
D. Data Access.
ANSWER: B
182. Which of the following problems bog down the development of data mining projects
A. Financial problem.
B. Lack of technical assistance.
C. Lack of long-term vision.
25
D. Legal and privacy restrictions.
ANSWER: C
183. _______ is the closeness of repeated measurements to one another.

A. Precision.
B. Bias.
C. Accuracy.
D. non-scientific.
ANSWER: A
184. Which of the following matrix consist asymmetric data?

A. Sparse data matrix.
B. Indentity matrix.
C. Confusion matrix.
D. Cross matrix.
ANSWER: A
185. Which of the following matrix consist asymmetric data?

A. Sparse data matrix.
B. Indentity matrix.
C. Confusion matrix.
D. Cross matrix.
ANSWER: A
186. You are given data about seismic activity in Japan, and you want to predict a magnitude of the
next earthquake, this is an example of
Supervised learning
Unsupervised learning
Serration
Dimensionality reduction
ANSWER: A
187. Algoritm is
A. It uses machine-learning technique. Here a program can learn from past experience.
B. Computational procedure that takes some values as input and procedure takes some value as
output
C. Science of making machines perform tasks that would require intelligence when performed by
humans
D. Processing procedure
ANSWER: A
188. The information on two attributes is displayed in ____________ in scatter diagram.

A. visualization space.
B. scatter space.
C. cartesian space.
D. interactive space.
ANSWER: C
189. K-nearest neighbor is one of the _______.

A. learning technique.
B. OLAP tool.
C. purest search technique.
D. data warehousing tool.
26
ANSWER: C
190. In K- nearest neighbor the input is translated to __________.

A. values
B. points in multidimensional space
C. strings of characters
D. nodes
ANSWER: B
191. What is a tag cloud?

A. Is a visualization of statistics of user-preferred order.
B. Collection of data objects.
C. Data analysis
D. Data mining application
Answer: A
192. Analysis of variance is a statistical method of comparing the ________ of several populations.
A. standard deviations
B. variances
C. means
D. proportions
Answer: A

A. Oracle.
B. DBZ.
C. Informix.
D. Redbrick.
ANSWER: D

ANSWER: A

A. Classification.
B. Regression.
ANSWER: C

A. Descriptive.
B. Predictive.
C. Regression.
ANSWER: A
27
28
http://grdmcqonline/printqp.php?heading=II M.Sc(IT) [2012-2014], Se...
Dr.G.R.Damodaran College of Science

(Autonomous, affiliated to the Bharathiar University, recognized by the UGC)Re-
accredited at the 'A' Grade Level by the NAAC and ISO 9001:2008 Certified
CRISL rated 'A' (TN) for MBA and MIB Programmes
II M.Sc(IT) [2012-2014]
Semester III
Core: Data Warehousing and Mining - 363U1
Multiple Choice Questions.
1. __________ is a subject-oriented, integrated, time-variant, nonvolatile collection of data in support

of management decisions.
A. Data Mining.
C. Web Mining.
D. Text Mining.
ANSWER: B

A. read only.
B. write only.
C. read write only.
D. none.
ANSWER: A

ANSWER: A
warehouse is___________.
B. time-variant.
C. integrated.
ANSWER: D
5. The time horizon in Data warehouse is usually __________.

A. 1-2 years.
B. 3-4years.
C. 5-6 years.
D. 5-10 years.
ANSWER: D

A. OLAP.
B. OLTP.
C. SMTP.
1 of 34 8/20/2013 2:47 PM
D. FTP.
ANSWER: B

A. Relational data.
C. Metadata.
ANSWER: C
8. ____________predicts future trends & behaviors, allowing business managers to make proactive,
knowledge-driven decisions.
A. Data warehouse.
B. Data mining.
C. Datamarts.
D. Metadata.
ANSWER: B

ANSWER: B

A. Oracle.
B. DBZ.
C. Informix.
D. Redbrick.
ANSWER: D
11. ________________defines the structure of the data held in operational databases and used by
operational applications.
ANSWER: C

ANSWER: B
users.
ANSWER: A
2 of 34 8/20/2013 2:47 PM
14. ______consists of formal definitions, such as a COBOL layout or a database schema.

A. Classical metadata.
B. Transformation metadata.
C. Historical metadata.
D. Structural metadata.
ANSWER: A
15. _____________consists of information in the enterprise that is not in classical form.

A. Mushy metadata.
B. Differential metadata.
C. Data warehouse.
D. Data mining.
ANSWER: A
16. . ______________databases are owned by particular departments or business groups.

A. Informational.
B. Operational.
C. Both informational and operational.
D. Flat.
ANSWER: B

A. one.
B. two.
C. three.
D. four.
ANSWER: A
18. The time horizon in operational environment is ___________.

A. 30-60 days.
B. 60-90 days.
C. 90-120 days.
D. 120-150 days.
ANSWER: B
19. The key used in operational environment may not have an element of__________.
A. time.
B. cost.
C. frequency.
D. quality.
ANSWER: A

A. data warehouse.
B. data mining.
C. operational.
D. informational.
ANSWER: C

A. OLTP
B. files
C. RDBMS
3 of 34 8/20/2013 2:47 PM
D. data warehouse
ANSWER: D

ANSWER: A
23. Data warehouse contains_____________data that is never found in the operational environment.
A. normalized.
B. informational.
C. summary.
D. denormalized.
ANSWER: C
24. Data redundancy between the environments results in less than ____________percent.
A. one.
B. two.
C. three.
D. four.
ANSWER: A
25. Bill Inmon has estimated___________of the time required to build a data warehouse, is consumed
in the conversion process.
A. 10 percent.
B. 20 percent.
C. 40 percent
D. 80 percent.
ANSWER: D

A. monoatomic data.
B. diatomic data.
C. atomic data.
ANSWER: C
27. _______test is used in an online transactional processing environment.

A. MEGA.
B. MICRO.
C. MACRO.
D. ACID.
ANSWER: D
28. ___________ is a good alternative to the star schema.

A. Star schema.
B. Snowflake schema.
C. Fact constellation.
D. Star-snowflake schema.
ANSWER: C
29. The biggest drawback of the level indicator in the classic star-schema is that it limits_________.
4 of 34 8/20/2013 2:47 PM
A. quantify.
B. qualify.
C. flexibility.
D. ability.
ANSWER: C

ANSWER: C
31. An operational system is _____________.

A. used to run the business in real time and is based on historical data.
B. used to run the business in real time and is based on current data.
C. used to support decision making and is based on current data.
D. used to support decision making and is based on historical data.
ANSWER: B

ANSWER: C
33. The active data warehouse architecture includes __________

ANSWER: D

ANSWER: B

eliminated.
eliminated.
ANSWER: A

5 of 34 8/20/2013 2:47 PM

ANSWER: B
37. Data scrubbing is _____________.

D. a process to upgrade the quality of data before it is moved into a data warehouse
ANSWER: D
38. The load and index is ______________.

D. a process to upgrade the quality of data before it is moved into a data warehouse.
ANSWER: B

ANSWER: A
40. ____________ is called a multifield transformation.

A. Converting data from one field into multiple fields.
B. Converting data from fields into field.
C. Converting data from double fields into multiple fields.
D. Converting data from one field to one field.
ANSWER: A
41. The type of relationship in star schema is __________________.

A. many-to-many.
B. one-to-one.
C. one-to-many.
D. many-to-one.
ANSWER: C
42. Fact tables are ___________.

A. completely demoralized.
B. partially demoralized.
C. completely normalized.
D. partially normalized.
ANSWER: C

ANSWER: A
44. Business Intelligence and data warehousing is used for ________.

A. Forecasting.
6 of 34 8/20/2013 2:47 PM
B. Data Mining.
ANSWER: D
45. The data administration subsystem helps you perform all of the following, except__________.
A. backups and recovery.
B. query optimization.
C. security management.
D. create, change, and delete information.
ANSWER: D
46. The most common source of change data in refreshing a data warehouse is _______.
A. queryable change data.
B. cooperative change data.
C. logged change data.
D. snapshot change data.
ANSWER: A
47. ________ are responsible for running queries and reports against data warehouse tables.
A. Hardware.
B. Software.
C. End users.
D. Middle ware.
ANSWER: C
48. Query tool is meant for __________.

A. data acquisition.
B. information delivery.
C. information exchange.
D. communication.
ANSWER: A

A. root node.
B. decision tree.
C. siblings.
D. branches.
ANSWER: B
ANSWER: B
51. ___________ is a method of incremental conceptual clustering.

A. CORBA.
B. OLAP.
C. COBWEB.
D. STING.
ANSWER: C
7 of 34 8/20/2013 2:47 PM
52. Effect of one attribute value on a given class is independent of values of other attribute is called
_________.
A. value independence.
B. class conditional independence.
C. conditional independence.
D. unconditional independence.
ANSWER: A
D. access to data.
ANSWER: C
54. Maintenance of cache consistency is the limitation of __________________.

A. NUMA.
B. UNAM.
C. MPP.
D. PMP.
ANSWER: C
55. Data warehouse architecture is based on ______________.

A. DBMS.
B. RDBMS.
C. Sybase.
D. SQL Server.
ANSWER: B
56. Source data from the warehouse comes from _______________.

A. ODS.
B. TDS.
C. MDDB.
D. ORDBMS.
ANSWER: A
57. ________________ is a data transformation process.

A. Comparison.
B. Projection.
C. Selection.
D. Filtering.
ANSWER: D
58. The technology area associated with CRM is _______________.

A. specialization.
B. generalization.
C. personalization.
D. summarization.
ANSWER: C
59. SMP stands for _______________.

A. Symmetric Multiprocessor.
B. Symmetric Multiprogramming.
C. Symmetric Metaprogramming.
8 of 34 8/20/2013 2:47 PM
D. Symmetric Microprogramming.
ANSWER: A
60. __________ are designed to overcome any limitations placed on the warehouse by the nature of the
D. Data repository.
ANSWER: C
61. __________ are designed to overcome any limitations placed on the warehouse by the nature of the
D. Data repository.
ANSWER: C
62. MDDB stands for ___________.

A. multiple data doubling.
B. multidimensional databases.
C. multiple double dimension.
D. multi-dimension doubling.
ANSWER: B

A. Metadata.
B. Microdata.
C. Minidata.
D. Multidata.
ANSWER: A

B. Repository.
D. Data dictionary.
ANSWER: C
65. EIS stands for ______________.

A. Extended interface system.
B. Executive interface system.
C. Executive information system.
D. Extendable information system.
ANSWER: C
66. ___________ is data collected from natural systems.

A. MRI scan.
B. ODS data.
C. Statistical data.
D. Historical data.
ANSWER: A
9 of 34 8/20/2013 2:47 PM
67. _______________ is an example of application development environments.

A. Visual Basic.
B. Oracle.
C. Sybase.
D. SQL Server.
ANSWER: A
B. deduplication.
C. disambiguation.
D. segmentation.
ANSWER: D
69. ____________ are some popular OLAP tools.

A. Metacube, Informix.
B. Oracle Express, Essbase.
C. HOLAP.
D. MOLAP.
ANSWER: A

A. retrospective.
B. interrogative.
C. predictive.
D. imperative.
ANSWER: C

A. Association.
B. Preferencing.
C. Segmentation.
D. Classification.
ANSWER: B
72. Strategic value of data mining is ______________.

A. cost-sensitive.
B. work-sensitive.
C. time-sensitive.
D. technical-sensitive.
ANSWER: C
73. ____________ proposed the approach for data integration issues.

A. Ralph Campbell.
B. Ralph Kimball.
C. John Raphlin.
D. James Gosling.
ANSWER: B
74. The terms equality and roll up are associated with ____________.
A. OLAP.
B. visualization.
C. data mart.
D. decision tree.
10 of 34 8/20/2013 2:47 PM
ANSWER: C

A. exception.
B. alerts.
C. errors.
D. bugs.
ANSWER: B
76. ____________ is a metadata repository.

A. Prism solution directory manager.
B. CORBA.
C. STUNT.
D. COBWEB.
ANSWER: A
77. ________________ is an expensive process in building an expert system.

A. Analysis.
B. Study.
C. Design.
D. Information collection.
ANSWER: D

ANSWER: B
79. The first International conference on KDD was held in the year _____________.
A. 1996.
B. 1997.
C. 1995.
D. 1994.
ANSWER: C

A. recovery.
B. data cleaning.
C. data cleansing.
D. data pruning.
ANSWER: B
81. ____________ contains information that gives users an easy-to-understand perspective of the
information stored in the data warehouse.
A. Business metadata.
B. Technical metadata.
D. Financial metadata.
ANSWER: A
system.
11 of 34 8/20/2013 2:47 PM
C. Data dictionary.
D. Database.
ANSWER: B

A. segmentation.
B. visualization.
C. correction.
D. association.
ANSWER: D
ANSWER: B
85. ____________ can generate programs itself, enabling it to carry out new tasks.
A. Automated system.
B. Decision making system.
C. Self-learning system.
D. Productivity system.
ANSWER: D
86. The power of self-learning system lies in __________.

A. cost.
B. speed.
C. accuracy.
D. simplicity.
ANSWER: C
87. Building the informational database is done with the help of _______.
A. transformation or propagation tools.
B. transformation tools only.
C. propagation tools only.
D. extraction tools.
ANSWER: A
88. How many components are there in a data warehouse?

A. two.
B. three.
C. four.
D. five.
ANSWER: D
89. Which of the following is not a component of a data warehouse?

A. Metadata.
B. Current detail data.
D. Component Key.
ANSWER: D
12 of 34 8/20/2013 2:47 PM
90. ________ is data that is distilled from the low level of detail found at the current detailed leve.
A. Highly summarized data.
C. Metadata.
ANSWER: B
91. Highly summarized data is _______.

A. compact and easily accessible.
B. compact and expensive.
C. compact and hardly accessible.
D. compact.
ANSWER: A
C. Metadata.
ANSWER: C
93. Metadata contains atleast _________.

A. the structure of the data.
B. the algorithms used for summarization.
C. the mapping from the operational environment to the data warehouse.
ANSWER: D
94. Which of the following is not a old detail storage medium?

B. RAID.
C. Microfinche.
D. Pen drive.
ANSWER: D
95. The data from the operational environment enter _______ of data warehouse.
B. Older detail data.
D. Highly summarized data.
ANSWER: A
96. The data in current detail level resides till ________ event occurs.
A. purge.
B. summarization.
C. archieved.
ANSWER: D

A. entities.
B. facts.
C. keys.
13 of 34 8/20/2013 2:47 PM
ANSWER: B
98. The granularity of the fact is the _____ of detail at which it is recorded.
A. transformation.
B. summarization.
C. level.
D. transformation and summarization.
ANSWER: C
99. Which of the following is not a primary grain in analytical modeling?

A. Transaction.
B. Periodic snapshot.
C. Accumulating snapshot.
ANSWER: B
100. Granularity is determined by ______.

A. number of parts to a key.
B. granularity of those parts.
C. both A and B.
D. none of the above.
ANSWER: C
101. ___________ of data means that the attributes within a given entity are fully dependent on the
entire primary key of the entity.
A. Additivity.
B. Granularity.
C. Functional dependency.
D. Dimensionality.
ANSWER: C
102. A fact is said to be fully additive if ___________.

ANSWER: A
103. A fact is said to be partially additive if ___________.

ANSWER: B
104. A fact is said to be non-additive if ___________.

ANSWER: C
105. Non-additive measures can often combined with additive measures to create new _________.
14 of 34 8/20/2013 2:47 PM
A. additive measures.
B. non-additive measures.
C. partially additive.
ANSWER: A
106. A fact representing cumulative sales units over a day at a store for a product is a _________.
A. additive fact.
B. fully additive fact.
C. partially additive fact.
D. non-additive fact.
ANSWER: B
107. ____________ of data means that the attributes within a given entity are fully dependent on the
entire primary key of the entity.
A. Additivity.
B. Granularity.
C. Functional Dependency.
D. Dependency.
ANSWER: C
108. Which of the following is the other name of Data mining?

ANSWER: D

A. Clustering.
B. Regression.
C. Summarization.
ANSWER: B

A. Classification.
B. Regression.
ANSWER: C

A. Descriptive.
B. Predictive.
C. Regression.
ANSWER: A

A. current data.
B. historical data.
D. assumptions.
15 of 34 8/20/2013 2:47 PM
ANSWER: B

A. Regression.
C. Prediction.
D. Classification.
ANSWER: D
A. Regression.
C. Prediction.
D. Classification.
ANSWER: B

A. Regression.
D. Prediction.
ANSWER: B

B. Summarization.
C. Clustering.
D. Prediction.
ANSWER: C
117. Link Analysis is otherwise called as ___________.

A. affinity analysis.
B. association rules.
C. both A & B.
D. Prediction.
ANSWER: C
118. _________ is a the input to KDD.

A. Data.
B. Information.
C. Query.
D. Process.
ANSWER: A

A. Data.
B. Information.
C. Query.
ANSWER: D

A. three.
B. four.
16 of 34 8/20/2013 2:47 PM
C. five.
D. six.
ANSWER: C

A. selection.
B. preprocessing.
C. transformation.
D. interpretation.
ANSWER: B
122. Converting data from different sources into a common format for processing is called as ________.
A. selection.
B. preprocessing.
C. transformation.
D. interpretation.
ANSWER: C

A. selection.
B. transformaion.
C. data mining.
D. interpretation.
ANSWER: D

A. outliers.
B. rare values.
ANSWER: A

A. Graphical.
B. Geometric.
C. Icon-based.
D. Pixel-based.
ANSWER: B
A. Induction.
B. Compression.
C. Approximation.
D. Substitution.
ANSWER: A
127. Describing some characteristics of a set of data by a general model is viewed as ____________
A. Induction.
B. Compression.
C. Approximation.
D. Summarization.
ANSWER: B
17 of 34 8/20/2013 2:47 PM
A. Induction.
B. Compression.
C. Approximation.
D. Summarization.
ANSWER: C
129. _______ are needed to identify training data and desired results.
A. Programmers.
B. Designers.
C. Users.
D. Administrators.
ANSWER: C
130. Overfitting occurs when a model _________.

A. does fit in future states.
B. does not fit in future states.
C. does fit in current state.
D. does not fit in current state.
ANSWER: B
131. The problem of dimensionality curse involves ___________.

A. the use of some attributes may interfere with the correct completion of a data mining task.
B. the use of some attributes may simply increase the overall complexity.
C. some may decrease the efficiency of the algorithm.
ANSWER: D

A. changing data.
B. noisy data.
C. outliers.
D. missing data.
ANSWER: B
133. ROI is an acronym of ________.

A. Return on Investment.
B. Return on Information.
C. Repetition of Information.
D. Runtime of Instruction
ANSWER: A
confidential.
A. authorized use.
ANSWER: B
A. Preprocessed.
B. Cleaned.
C. Real-world.
D. Transformed.
18 of 34 8/20/2013 2:47 PM
ANSWER: C
136. The rise of DBMS occurred in early ___________.

A. 1950's.
B. 1960's
C. 1970's
D. 1980's.
ANSWER: C
137. SQL stand for _________.

A. Standard Query Language.
B. Structured Query Language.
C. Standard Quick List.
D. Structured Query list.
ANSWER: B
138. Which of the following is not a data mining metric?

A. Space complexity.
B. Time complexity.
C. ROI.
ANSWER: D
139. Reducing the number of attributes to solve the high dimensionality problem is called as ________.
C. cleaning.
D. Overfitting.
ANSWER: B
A. missing data.
B. changing data.
C. irrelevant data.
D. noisy data.
ANSWER: C

A. Sampling.
B. Parallelization
C. Both A & B.
ANSWER: C
142. Market-basket problem was formulated by __________.

A. Agrawal et al.
B. Steve et al.
C. Toda et al.
D. Simon et al.
ANSWER: A

A. inventory management.
B. sales promotion strategies.
19 of 34 8/20/2013 2:47 PM
C. marketing strategies.
ANSWER: D
144. The proportion of transaction supporting X in T is called _________.

A. confidence.
B. support.
C. support count.
ANSWER: B

A. confidence.
B. support.
C. support count.
ANSWER: C
146. The value that says that transactions in D that support X also support Y is called ______________.
A. confidence.
B. support.
C. support count.
ANSWER: A
147. If T consist of 500000 transactions, 20000 transaction contain bread, 30000 transaction contain
jam, 10000 transaction contain both bread and jam. Then the support of bread and jam is _______.
A. 2%
B. 20%
C. 3%
D. 30%
ANSWER: A
148. 7 If T consist of 500000 transactions, 20000 transaction contain bread, 30000 transaction contain
jam, 10000 transaction contain both bread and jam. Then the confidence of buying bread with jam is
_______.
A. 33.33%
B. 66.66%
C. 45%
D. 50%
ANSWER: D

A. consequent.
B. onset.
C. antecedent.
D. precedent.
ANSWER: C

A. consequent.
B. onset.
C. antecedent.
D. precedent.
20 of 34 8/20/2013 2:47 PM
ANSWER: A
ANSWER: D
_____________.
A. border set.
B. frequent set.
D. lattice.
ANSWER: B
B. border set.
C. lattice.
D. infrequent sets.
ANSWER: A
154. Any subset of a frequent set is a frequent set. This is ___________.

A. Upward closure property.
B. Downward closure property.
C. Maximal frequent set.
D. Border set.
ANSWER: B
155. Any superset of an infrequent set is an infrequent set. This is _______.

A. Maximal frequent set.
B. Border set.
ANSWER: C
156. If an itemset is not a frequent set and no superset of this is a frequent set, then it is _______.
A. Maximal frequent set
B. Border set.
ANSWER: B

A. width-wise algorithm.
B. level-wise algorithm.
C. pincer-search algorithm.
D. FP growth algorithm.
ANSWER: B

A. top-down search.
21 of 34 8/20/2013 2:47 PM
B. breadth first search.

C. depth first search.
D. bottom-up search.
ANSWER: D

C. Pruning.
D. Partitioning.
ANSWER: A

C. Pruning.
D. Partitioning.
ANSWER: C
161. The _______ step eliminates the extensions of (k-1)-itemsets which are not found to be frequent,
from being considered for counting support.
B. Pruning.
C. Partitioning.
D. Itemset eliminations.
ANSWER: B
A. upward.
B. downward.
C. breadthwise.
D. both upward and downward.
ANSWER: A

A. Only candidate set.
B. No candidate set.
C. Only border set.
D. No border set.
ANSWER: B

A. increases with the size of the maximum frequent set.
B. decreases with increase in size of the maximum frequent set.
C. increases with the size of the data.
D. decreases with the increase in size of the data.
ANSWER: A
165. MFCS is the acronym of _____.

A. Maximum Frequency Control Set.
B. Minimal Frequency Control Set.
C. Maximal Frequent Candidate Set.
D. Minimal Frequent Candidate Set.
ANSWER: C
22 of 34 8/20/2013 2:47 PM
166. Dynamuc Itemset Counting Algorithm was proposed by ____.

A. Bin et al.
B. Argawal et at.
C. Toda et al.
D. Simon et at.
ANSWER: A
167. Itemsets in the ______ category of structures have a counter and the stop number with them.
A. Dashed.
B. Circle.
C. Box.
D. Solid.
ANSWER: A
168. The itemsets in the _______category structures are not subjected to any counting.
A. Dashes.
B. Box.
C. Solid.
D. Circle.
ANSWER: C
169. Certain itemsets in the dashed circle whose support count reach support value during an iteration
move into the ______.
A. Dashed box.
B. Solid circle.
C. Solid box.
ANSWER: A
170. Certain itemsets enter afresh into the system and get into the _______, which are essentially the
supersets of the itemsets that move from the dashed circle to the dashed box.
A. Dashed box.
B. Solid circle.
C. Solid box.
D. Dashed circle.
ANSWER: D
171. The itemsets that have completed on full pass move from dashed circle to ________.
A. Dashed box.
B. Solid circle.
C. Solid box.
ANSWER: B
172. The FP-growth algorithm has ________ phases.

A. one.
B. two.
C. three.
D. four.
ANSWER: B
173. A frequent pattern tree is a tree structure consisting of ________.

A. an item-prefix-tree.
23 of 34 8/20/2013 2:47 PM
B. a frequent-item-header table.
C. a frequent-item-node.
D. both A & B.
ANSWER: D
174. The non-root node of item-prefix-tree consists of ________ fields.

A. two.
B. three.
C. four.
D. five.
ANSWER: B
175. The frequent-item-header-table consists of __________ fields.

A. only one.
B. two.
C. three.
D. four.
ANSWER: B
176. The paths from root node to the nodes labelled 'a' are called __________.
A. transformed prefix path.
B. suffix subpath.
C. transformed suffix path.
D. prefix subpath.
ANSWER: D
177. The transformed prefix paths of a node 'a' form a truncated database of pattern which co-occur
with a is called _______.
A. suffix path.
B. FP-tree.
C. conditional pattern base.
D. prefix path.
ANSWER: C
B. Classification.
C. Clustering.
ANSWER: C
179. Which of the following is a clustering algorithm?

A. A priori.
B. CLARA.
C. Pincer-Search.
D. FP-growth.
ANSWER: B
180. _______ clustering technique start with as many clusters as there are records, with each cluster
having only one record.
A. Agglomerative.
B. divisive.
C. Partition.
D. Numeric.
24 of 34 8/20/2013 2:47 PM
ANSWER: A
cluster into small pieces.
A. Agglomerative.
B. Divisive.
C. Partition.
D. Numeric.
ANSWER: B
182. Which of the following is a data set in the popular UCI machine-learning repository?
A. CLARA.
B. CACTUS.
C. STIRR.
D. MUSHROOM.
ANSWER: D
A. k-medoid.
B. k-means.
C. STIRR.
D. ROCK.
ANSWER: B
184. In ___________ each cluster is represented by one of the objects of the cluster located near the
center.
A. k-medoid.
B. k-means.
C. STIRR.
D. ROCK.
ANSWER: A

A. DBSCAN.
B. BIRCH.
C. PAM.
D. CURE.
ANSWER: C

A. DBSCAN
B. BIRCH.
C. PAM.
D. CURE.
ANSWER: A
187. CLARANS stands for _______.

A. CLARA Net Server.
B. Clustering Large Application RAnge Network Search.
C. Clustering Large Applications based on RANdomized Search.
D. CLustering Application Randomized Search.
ANSWER: C
188. BIRCH is a ________.
25 of 34 8/20/2013 2:47 PM
A. agglomerative clustering algorithm.

B. hierarchical algorithm.
C. hierarchical-agglomerative algorithm.
D. divisive.
ANSWER: C
189. The cluster features of different subclusters are maintained in a tree called ___________.
A. CF tree.
B. FP tree.
C. FP growth tree.
D. B tree.
ANSWER: A
190. The ________ algorithm is based on the observation that the frequent sets are normally very few
in number compared to the set of all itemsets.
A. A priori.
B. Clustering.
C. Association rule.
D. Partition.
ANSWER: D
191. The partition algorithm uses _______ scans of the databases to discover all frequent sets.
A. two.
B. four.
C. six.
D. eight.
ANSWER: A
scans the database.
A. candidate.
B. primary.
C. secondary.
D. superkey.
ANSWER: A
products.
A. Apriori algorithm.
B. Partition algorithm.
C. Distributed algorithm.
D. Pincer-search algorithm.
ANSWER: A
194. An algorithm called________is used to generate the candidate item sets for each pass after the
first.
A. apriori.
B. apriori-gen.
C. sampling.
D. partition.
ANSWER: B
195. The basic partition algorithm reduces the number of database scans to ________ & divides it into
partitions.
26 of 34 8/20/2013 2:47 PM
A. one.
B. two.
C. three.
D. four.
ANSWER: B
196. ___________and prediction may be viewed as types of classification.

A. Decision.
B. Verification.
C. Estimation.
D. Illustration.
ANSWER: C
197. ___________can be thought of as classifying an attribute value into one of a set of possible
classes.
A. Estimation.
B. Prediction.
C. Identification.
D. Clarification.
ANSWER: B
198. Prediction can be viewed as forecasting a_________value.

A. non-continuous.
B. constant.
C. continuous.
D. variable.
ANSWER: C
199. _________data consists of sample input data as well as the classification assignment for the data.
A. Missing.
B. Measuring.
C. Non-training.
D. Training.
ANSWER: D
A. if-then.
B. while.
C. do while.
D. switch.
ANSWER: A
201. ____________ are a different paradigm for computing which draws its inspiration from
neuroscience.
A. Computer networks.
B. Neural networks.
C. Mobile networks.
D. Artificial networks.
ANSWER: B
202. The human brain consists of a network of ___________.

A. neurons.
B. cells.
C. Tissue.
27 of 34 8/20/2013 2:47 PM
D. muscles.
ANSWER: A
203. Each neuron is made up of a number of nerve fibres called _____________.

A. electrons.
B. molecules.
C. atoms.
D. dendrites.
ANSWER: D
204. The ___________is a long, single fibre that originates from the cell body.
A. axon.
B. neuron.
C. dendrites.
D. strands.
ANSWER: A
205. A single axon makes ___________ of synapses with other neurons.

A. ones.
B. hundreds.
C. thousands.
D. millions.
ANSWER: C
206. _____________ is a complex chemical process in neural networks.

A. Receiving process.
B. Sending process.
C. Transmission process.
D. Switching process.
ANSWER: C
207. _________ is the connectivity of the neuron that give simple devices their real power. a. b. c. d.
A. Water.
B. Air.
C. Power.
D. Fire.
ANSWER: D
208. __________ are highly simplified models of biological neurons.

A. Artificial neurons.
B. Computational neurons.
C. Biological neurons.
D. Technological neurons.
ANSWER: A
209. The biological neuron's _________ is a continuous function rather than a step function.
A. read.
B. write.
C. output.
D. input.
ANSWER: C
210. The threshold function is replaced by continuous functions called ________ functions.
A. activation.
28 of 34 8/20/2013 2:47 PM
B. deactivation.
C. dynamic.
D. standard.
ANSWER: A
211. The sigmoid function also knows as __________functions.

A. regression.
B. logistic.
C. probability.
D. neural.
ANSWER: B
212. MLP stands for ______________________.

A. mono layer perception.
B. many layer perception.
C. more layer perception.
D. multi layer perception.
ANSWER: D
213. In a feedforward networks, the conncetions between layers are ___________ from input to
output.
A. bidirectional.
B. unidirectional.
C. multidirectional.
D. directional.
ANSWER: B
214. The network topology is constrained to be __________________.

A. feedforward.
B. feedbackward.
C. feed free.
D. feed busy.
ANSWER: A
215. RBF stands for _____________.

A. Radial basis function.
B. Radial bio function.
C. Radial big function.
D. Radial bi function.
ANSWER: A
216. RBF have only _______________ hidden layer.

A. four.
B. three.
C. two.
D. one.
ANSWER: D
217. RBF hidden layer units have a receptive field which has a ____________; that is, a particular input
value at which they have a maximal output.
A. top.
B. bottom.
C. centre.
D. border.
29 of 34 8/20/2013 2:47 PM
ANSWER: C
values does not exist.
A. Competitive.
B. Perception.
C. Supervised.
D. Unsupervised.
ANSWER: D
219. ___________ employs the supervised mode of learning.

A. RBF.
B. MLP.
C. MLP & RBF.
D. ANN.
ANSWER: C
220. ________________ design involves deciding on their centres and the sharpness of their Gaussians.
A. DR.
B. AND.
C. XOR.
D. RBF.
ANSWER: D
221. ___________ is the most widely applied neural network technique.

A. ABC.
B. PLM.
C. LMP.
D. MLP.
ANSWER: D
222. SOM is an acronym of _______________.

A. self-organizing map.
B. self origin map.
C. single organizing map.
D. simple origin map.
ANSWER: A
223. ____________ is one of the most popular models in the unsupervised framework.
A. SOM.
B. SAM.
C. OSM.
D. MSO.
ANSWER: A
224. The actual amount of reduction at each learning step may be guided by _________.
A. learning cost.
B. learning level.
C. learning rate.
D. learning time.
ANSWER: C
225. The SOM was a neural network model developed by ________.

A. Simon King.
30 of 34 8/20/2013 2:47 PM
B. Teuvokohonen.
C. Tomoki Toda.
D. Julia.
ANSWER: B
226. SOM was developed during ____________.

A. 1970-80.
B. 1980-90.
C. 1990 -60.
D. 1979 -82.
ANSWER: D
227. Investment analysis used in neural networks is to predict the movement of _________ from
previous data.
A. engines.
B. stock.
C. patterns.
D. models.
ANSWER: B
228. SOMs are used to cluster a specific _____________ dataset containing information about the
patient's drugs etc.
A. physical.
B. logical.
C. medical.
D. technical.
ANSWER: C
229. GA stands for _______________.

A. Genetic algorithm
B. Gene algorithm.
C. General algorithm.
D. Geo algorithm.
ANSWER: A
230. GA was introduced in the year __________.

A. 1955.
B. 1965.
C. 1975.
D. 1985.
ANSWER: C
231. Genetic algorithms are search algorithms based on the mechanics of natural_______.
A. systems.
B. genetics.
C. logistics.
D. statistics.
ANSWER: B
232. GAs were developed in the early _____________.

A. 1970.
B. 1960.
C. 1950.
D. 1940.
31 of 34 8/20/2013 2:47 PM
ANSWER: A
233. The RSES system was developed in ___________.

A. Poland.
B. Italy.
C. England.
D. America.
ANSWER: A
234. Crossover is used to _______.

ANSWER: A
235. The mutation operator ______.

ANSWER: B
236. Which of the following is an operation in genetic algorithm?

A. Inversion.
B. Dominance.
C. Genetic edge recombination.
ANSWER: D
237. . ___________ is a system created for rule induction.

A. RBS.
B. CBS.
C. DBS.
D. LERS.
ANSWER: D
238. NLP stands for _________.

A. Non Language Process.
B. Nature Level Program.
C. Natural Language Page.
D. Natural Language Processing.
ANSWER: D
A. text.
B. web.
C. page.
D. level.
ANSWER: B

A. graphics.
B. multimedia.
32 of 34 8/20/2013 2:47 PM
C. meta.
D. digital.
ANSWER: B
241. _______ mining is concerned with discovering the model underlying the link structures of the web.
A. Data structure.
B. Web structure.
C. Text structure.
D. Image structure.
ANSWER: B

C. Social network.
D. Logical network.
ANSWER: C
243. The ________ propose a measure of standing a node based on path counting.
A. open web.
B. close web.
C. link web.
D. hidden web.
ANSWER: B
A. clustering.
B. associations.
D. classification.
ANSWER: A
245. In web mining, _________ is used to know the order in which URLs tend to be accessed.
A. clustering.
B. associations.
D. classification.
ANSWER: C
A. clustering.
B. associations.
D. classification.
ANSWER: B
ANSWER: A
33 of 34 8/20/2013 2:47 PM

ANSWER: B
249. A link is said to be _________ link if it is between pages with different domain names.
A. intrinsic.
B. transverse.
C. direct.
D. contrast.
ANSWER: B
250. A link is said to be _______ link if it is between pages with the same domain name.
A. intrinsic.
B. transverse.
C. direct.
D. contrast.
ANSWER: A
Staff Name
LAXMI.SREE.B.R.
34 of 34 8/20/2013 2:47 PM
marks question A B C D ans
Data warehousing
involves data
cleaning, data
integration, and
data
consolidations. To
integrate
To integrate heterogeneous databases, how many
0 1 2 3 4 5 heterogeneous
approaches are there in Data Warehousing?
databases, we
have the following
two approaches:
Query Driven
Approach,
Update Driven
Approach
Evolution
Analysis:
Evolution analysis
refers to the
__________ refers to the description and model
description and
1 1 regularities or trends for objects whose behavior Evolution Analysis Outlier Analysis Prediction Classification
model regularities
changes over time.
or trends for
objects whose
behavior changes
over time.
Data
Discrimination: It
refers to the
The mapping or classification of a class with Data Data Data Sub mapping or
2 1 Data Set
some predefined group or class is known as? Discrimination Characterization Structure classification of a
class with some
predefined group
or class
Data Integration:
In which step of Knowledge Discovery, multiple Data multiple data
3 1 Data Integration Data Cleaning Data Selection
data sources are combined? Transformation sources are
combined.
Time-Sensitive is
Technical-
4 1 What is the strategic value of data mining? Time-sensitive Work-sensitive. Cost-sensitive the strategic value
sensitive.
of data mining.
The first step
involved in the
The first step involved in knowledge discovery Data
5 2 Data Cleaning Data Selection Data Transformation knowledge
is? Integration
discovery is Data
Integration.
Selection and
Which of the following is not a data mining Selection and Classification and Characterization Clustering and interpretation is
6 2
functionality? interpretation regression and Discrimination Analysis not a function of
data mining
Data
Characterization:
This refers to
summarizing data
In Data Characterization, the class under study is
7 2 Target Class Initial Class Study Class Final Class of class under
called as?
study. This class
under study is
called Target
Class.
The predictive
Capability of data mining is to build model has the
8 2 Predictive. Interrogative. Retrospective. Imperative.
___________ models. capability of data
mining
The database may
contain complex
data objects,
Mining multimedia data
"Handling of relational and complex types of Diverse Data Performance Methodology and objects, spatial
9 2 None
data" issue comes under? Types Issues Issues User Interaction data, temporal
Issues data, etc. One
system can't mine
all this kind of
data.
Data Mining is
defined as
extracting
information from
Data mining also Data Mining is huge sets of data.
involves other defined as the In other words,
Data mining is the
processes such procedure of we can say that
procedure of mining
10 2 What is true about data mining? All as Data Cleaning, extracting data mining is the
knowledge from
Data Integration, information procedure of
data.
Data from huge sets mining knowledge
Transformation of data from data. The
information or
knowledge is
extracted so that it
can be used.
The KDD stands
Knowledge
Knowledge Knowledge Data Knowledge for Knowledge
11 2 What is KDD Discovery
Database House Data Definition Discovery
Database
Database.
Data mining is
highly useful in the
following domains:
Corporate Market Market Analysis
Which of the following is the correct application
12 2 All Analysis & Risk Fraud Detection Analysis and and Management,
of data mining?
Management Management Corporate
Analysis & Risk
Management,
Fraud Detection
All of the above
Which of the following is not a data mining Space
13 2 All Time complexity. ROI are algorithm
metric? complexity.
metrics.
The Data Mining
Query Language
(DMQL) was
Data Marts
Data Mining Query Dataset Mining DBMiner Query proposed by Han,
14 2 DMQL stands for? Query
Language Query Language Language Fu, Wang, et al.
Language
for the DBMiner
data mining
system.
Mining of
Correlations: It is
a kind of
additional analysis
performed to
uncover interesting
statistical
correlations
The analysis performed to uncover interesting
Mining of Mining of Mining of between
15 2 statistical correlations between associated- None
Correlations Clusters Association associated-
attribute-value pairs is called?
attribute-value
pairs or between
two item sets to
analyze that if they
have positive,
negative, or no
effect on each
other.
Data cleaning is a
technique that is
applied to remove
the noisy data and
correct the
inconsistencies in
data. Data
cleaning involves
Correct the Transformations to transformations to
To remove the
16 2 What is the use of data cleaning? All inconsistencies in correct the wrong correct the wrong
noisy data
data data. data. Data
cleaning is
performed as a
data
preprocessing
step while
preparing the data
for a data
warehouse.
In order to
effectively extract
the information
Mining from a huge
"Efficiency and scalability of data mining Performance Methodology Diverse Data Types amount of data in
17 2 None
algorithms" issues come under? Issues and User Issues databases, the
Interaction Issues data mining
algorithm must be
efficient and
scalable.
All are the
Sales promotion Marketing Inventory
18 3 Data mining helps in __________. All properties of data
strategies. strategies. management.
mining
Outlier Analysis:
Outliers may be
defined as the
__________ may be defined as the data objects data objects that
Evolution
19 3 that do not comply with the general behavior or Outlier Analysis Prediction Classification do not comply
Analysis
model of the data available. with the general
behavior or model
of the data
available.
……………………….. is a comparison of the
Data
general features of the target class data objects Data Data
20 3 Data discrimination Data selection discrimination is
against the general features of objects from one Classification Characterization
the feature
or multiple contrasting classes.
Frequent
Subsequence: A
sequence of
patterns that occur
A sequence of patterns that occur frequently is Frequent . Frequent Item Frequent Sub All of the
21 3 frequently such as
known as? Subsequence Set Structure above
purchasing a
camera is
followed by a
memory card.
Data mining is an
-------- is an essential process where intelligent Data
22 3 Data mining Text mining Data selection essential process
methods are applied to extract data patterns. warehousing
where AI is used.
Pattern evaluation:
The patterns
discovered should
Mining
be interesting
Methodology and Performance Diverse Data Types None of the
23 3 Does the pattern evaluation issue come under? because either
User Interaction Issues Issues above
they represent
Issues
common
knowledge or lack
of novelty.
What predicts future trends & behaviors, Data mining
24 3 allowing business managers to make Data mining. Data warehouse. Datamarts. Metadata. predicts future
proactive,knowledge-driven decisions. trends.
All the above are
Which of the following is the other name of Data Data-driven Exploratory
25 3 All Deductive learning. the name of data
mining? discovery. data analysis.
mining
There are two
categories of
functions involved
How many categories of functions involved in
26 3 2 3 4 5 in Data Mining: 1.
Data Mining?
Descriptive, 2.
Classification and
Prediction
A data mining
system can be
classified
according to the
following criteria:
Database
Does Data Mining System Classification consist Machine Database
27 3 All Information Science Technology,
of? Learning Technology
Statistics,
Machine Learning,
Information
Science,
Visualization,
Other Disciplines
The Query
It is very Driven All statements are
This approach is
Which of the following is the correct inefficient and Approach a disadvantage of
expensive for
28 3 disadvantage of the Query-Driven Approach in All very expensive needs complex the Query-Driven
queries that require
Data Warehousing? for frequent integration and Approach in Data
aggregations.
queries. filtering Warehousing.
processes.
The data can be
copied,
Both A and B are
processed,
the advantages of
Which of the following is the correct advantage integrated, This approach
the Update-
29 3 of the Update-Driven Approach in Data Both A and B annotated, provides high None
Driven Approach
Warehousing? summarized, and performance.
in Data
restructured in
Warehousing.
the semantic data
store in advance.
{ (item name,
SELECT item name, color, clothes SIZE,
color, clothes
SUM(quantity)\nFROM sales\nGROUP BY
30 1 4 8 2 1 size), (item name,
rollup(item name, color, clothes SIZE);\nHow
color), (item
many grouping is possible in this rollup?\n
name), () }.
We can change
the dimensions
used in a cross
The operation of changing the dimensions used in tab. The operation
31 1 Pivoting Alteration Piloting Renewing
a cross-tab is called as ________ of changing a
dimension used in
a cross-tab is
called pivoting.
OLAP is the
Online manipulation of
Online analytical Online analysis Online transaction
32 1 OLAP stands for aggregate information to
processing processing processing
processing support decision
making.
In OLAP, analysts
cannot view a
dimension in
different levels of
State true or false: In OLAP, analysts cannot
33 1 "False" "True" None None detail. The
view a dimension in different levels of detail.
different levels of
detail are
classified into a
hierarchy.
Given a relation
used for data
analysis, we can
identify some of its
attributes as
Data that can be modeled as dimension attributes
34 1 Multidimensional Singledimensional Measured Dimensional measure
and measure attributes are called _______ data.
attributes, since
they measure
some value, and
can be aggregated
upon.
Analysis of large
Business Intelligence and data warehousing is All are used in
35 1 All Data Mining. volumes of product Forecasting
used for ________. data ware house
sales data.
OLAP systems
permit users to
view the data at
any level of
granularity. The
The operation of moving from coarser granular
36 1 Drill down Increment Rollback Reduction process of moving
data to finer granular data is called _______
from finer granular
data to coarser
granular data is
called as drill-
down.
The opposite
operation—that of
moving from
The operation of moving from finer-granularity
coarser-
37 2 data to a coarser granularity (using aggregation) Rollup Drill down Dicing Pivoting
granularity data to
is called a ________
finer-granularity
data—is called a
drill down.
OLAP systems
can be
implemented as
client-server
State true or false: OLAP systems can be systems. Most of
38 2 "True" "False" None None
implemented as client-server systems the current OLAP
systems are
implemented as
client-server
systems.
Data that can be
modeled as
Data that can be modelled as dimension dimension
Multi-dimensional Mono-
39 2 attributes and measure attributes are called Measurable data Efficient data attributes and
data dimensional data
___________ measure attributes
are called multi-
dimensional data.
The slice
operation selects
one particular
dimension from a
given cube and
The process of viewing the cross-tab (Single Both Slicing provides a new
40 2 Slicing Dicing Pivoting
dimensional) with a fixed value of one attribute is and Dicing sub-cube. Dice
selects two or
more dimensions
from a given cube
and provides a
new sub-cube.
The time horizon in Data warehouse is usually 5 to 10 years is
41 2 5-10 years. 3-4 years 5-6 years. 1-2 years.
__________. the horizon time
Cross-tabs
enables analysts to
view two
How many dimensions of multi-dimensional data dimensions of
42 2 2 1 3 None
do cross tabs enable analysts to view? multi-dimensional
data, along with
the summaries of
the data.
Operational OLAP support
43 2 What do data warehouses support? OLAP OLTP OLAP and OLTP
databases data warehouses
RDBMS is the
Data warehouse architecture is based on
44 2 RDBMS DBMS Sybase. SQL Server data warehouse
______________.
architecture.
What does collector_type_id stands for in the
collector_type_uid
following code snippet?
45 2 uniqueidentifier membership role directory None is the GUID for
core.sp_remove_collector_type [
the collector type.
@collector_type_uid = ] ‘collector_type_uid’
Each cell in the
cube is identified
The generalization of cross-tab which is
Two-dimensional Multidimensional for the values for
46 2 represented visually is ____________ which is N-dimensional cube Cuboid
cube cube the three-
also called as a data cube.
dimensional
attributes.
Operational
The source of all data warehouse data is Operational Informal Formal Technology environment is the
47 2
the____________. environment. environment. environment. environment source of data
warehouse
A normalized
histogram. p(rk) =
nk / n\nWhere, n
is total number of
pixels in image, rk
the kth gray level
What is the sum of all components of a
48 3 1 -1 0 None and nk total pixels
normalized histogram?
with gray level
rk.\nHere, p(rk)
gives the
probability of
occurrence of
rk.\n
HOLAP means
Hybrid OLAP,
MOLAP means
multidimensional
Which of the following OLAP systems do not OLAP, ROLAP
49 3 None MOLAP ROLAP HOLAP
exist? means relational
OLAP. This
means all of the
above OLAP
systems exist.
We want to add the following capabilities to
Table2: show the data for 3 age groups (20-39, Between 40
Between 10 and 30 More than 100 is
40-60, over 60), 3 revenue groups (less than and 60
50 3 More than 100 4 (boundaries the capabilities to
$10,000, $10,000-$30,000, over $30,000) and (boundaries
includeD. Table2
add a new type of account: Money market. The includeD.
total number of measures will be:
The decode
function allows
substitution of
values in an
attribute of a
tuple. The decode
The _______ function allows substitution of function does not
51 3 Decode Unknown Cube Substitute
values in an attribute of a tuple always work as
we might like for
null values
because
predicates on null
values evaluate to
unknown.
OLAP systems
permit users to
view the data at
any level of
The operation of moving from finer granular data granularity. The
52 3 Roll up Increment Reduction Drill down
to coarser granular data is called _______ process of moving
from finer granular
data to coarser
granular data is
called as a roll-up.
OLAP is the
The ___________ engine for a data warehouse
53 3 OLAP SMTP NNTP POP engine of data
supports query-triggered usage of data
warehouse
Pivot
(sum(quantity) for
54 3 In SQL the cross-tabs are created using Slice Dice Pivot All color in
(’dark’,’pastel’,’
white’)).
DECODE The right synatax
DECODE DECODE (search, for DECODE is
DECODE (search,
(expression, (expression, expression, DECODE
Which one of the following is the right syntax for result [, search,
55 3 search, result [, result [, search, result [, (expression,
DECODE? result]… [, default],
search, result]… [, result]… [, search, search, result [,
expression)
default]) default], search) result]… [, search, result]…
default]) [, default])
800,000 is value
at the intersection
The value at the intersection of the row labeled
of the row labeled
56 3 "India" and the column "Savings" in Table2 should 800000 300000 200000 300000
"India" and the
be:
column "Savings"
in Table2
The heart of data
Data warehouse Data mining Data mart database Relational data warehouse is Data
57 3 __________ is the heart of the warehouse.
database servers database servers. servers. base servers. warehouse
database servers.
{ (item name, color, clothes size), (item name,
Group by the Group by ‘Group by cube’
58 3 color), (item name, clothes size), (color, clothes None Group by
cubic rollup is used.
size), (item name), (color), (clothes size), () }
The data
59 3 The data Warehouse is__________. Read-only. Write only. Read write only None warehouse is
read-only
Unsupervised data
Unsupervised data Supervised data Depends on the
60 1 Cluster analysis is a type of ... ? Can not say mining is the
mining mining data
cluster analysis
High All are the
61 1 Challenges of clustering includes? All Scalability Noisy data dimensionality challenges of
of data clustering
You should
Continuous – Continuous – choose a
Binary – manhattan
62 1 Which of the following combination is incorrect? None correlation euclidean distance/similarity
distance
similarity distance that makes sense
for your problem.
Hierarchical
Hierarchical clustering should be primarily used
63 1 "True" "False" None None clustering is
for exploration.
deterministic.
Reduction of All mention are
In clustering high dimensional data comes with Reduction in Increase in
64 1 All algorithm the problems od
problems like? algorithm efficiency complexity
performance clustering
Hierarchical
Which of the following clustering requires clustering requires
65 1 Hierarchical Partitional Naive Bayes None
merging approach? a defined distance
as well.
K-means
Which of the following is required by K-means Number of Initial guess as to Defined clustering follows
66 1 All
clustering? clusters cluster centroids distance metric the partitioning
approach.
Hierarchical
Which clustering procedure is characterized by Hierarchical Optimizing Partition based Density
67 1 clustering is tree
the formation of a tree like structure? clustering partitioning clustering clustering
like structure.
k-means
k-means clustering k-nearest
k-nearest neighbor clustering is a
aims to partition n neighbor has
68 1 Point out the wrong statement. is same as k- none er method of
observations into k nothing to do with
means vector
clusters k-means.
quantization
Dissimilarity
A metric that is
means metric used
used to measure A metric that is used
69 2 What is dissimilarity? Both a and b None in clustering and
the closeness of in clustering.
closeness of
objects.
objects.
Formulating the
Data
The most important part of ... is selecting the Formulating the Deciding the Analysing the clustering problem
70 2 preprocessing for
attributes on which clustering is done? clustering problem clustering procedure cluster is the imporatant
clustering
part of clustering.
K-means
clustering
K-means is not deterministic and it also consists
71 2 "True" "False" None None produces the final
of number of iterations.
estimate of cluster
centroids.
Non-hierarchical
Non-hierarchical Optimizing Agglomerative clustering is called
72 2 k-means clustering is also referred to as ....? Divisive clustering
clustering partitioning clustering as k-means
clustering
Partition All other are the
73 2 Which is not a type of clustering? Decision driven Similarity based Density based
Based type of clustering
Hierarchical
Tree showing how
Which of the following is finally produced by Final estimate of Assignment of each clustering is an
74 2 close things are to All
Hierarchical Clustering? cluster centroids point to clusters agglomerative
each other
approach.
Derivative is not a
Which of the following is not clustering
75 2 Derivative Agglomerative Partitioning Density Based clustering
technique?
technique.
K-means requires
Which of the following function is used for k-
76 2 k-means k-mean heatmap None a number of
means clustering?
clusters.
Cluster
analysis
reduces the
number of
In clustering,
In clustering, larger objects, not
The dendrogram Clustering should be larger the distance
Which of the below sentences is true with respect the distance the the number of
77 2 is read from right done on samples of the more similar
of clustering? more similar the variables, by
to left 300 or more the object is true
object grouping them
for clustering.
into a much
smaller
number of
clusters
Unsupervised is a
78 2 Clustering is what type of learning? Unsupervised supervised Semi-supervised None
type of learning
Some elements
The choice of may be close to
In general, the an appropriate one another
Hierarchical
merges and splits metric will according to one
79 2 Point out the correct statement. All clustering is also
are determined in a influence the distance and
called HCA
greedy manner shape of the farther away
clusters according to
another.
Hierarchical
clustering is
Hierarchical clustering is slower than non-
80 2 "True" "False" Depends on data Can not say slower than non-
hierarchical clustering?
hierarchical
clustering
It does not fit in It does not fit in
It does not fit in It does not fit in
81 3 When does a model is said to do over-fitting? both current and None future state is a
future state current state
future state model.
The group of
Group of similar
Group objects Simplification of similar objects
objects with
having a similar data to make it with significant
significant
82 3 What is a cluster? feature from a ready for a None dissimilarity with
dissimilarity with
group of similar classification objects of other
objects of other
objects. algorithm. groups is called as
groups
cluster
Cluster analysis is
not classify
Which method of analysis does not classify Discriminant Regression
83 3 Cluster analysis Analysis of variance variables as
variables as dependent or independent? analysis analysis
dependent or
independent
Groups are not
Groups are not Groups are Depends on the
84 3 In clustering ? Can not say predefined in
predefined predefined data
clustering
All are the
85 3 Which of the following are clustering techniques? All Density Based Partitioning Agglomerative clustering
techniques.
Process of Process of Clustering is a
None of the
86 3 What is clustering? grouping similar classifying new Both a and b group of similar
above
objects object objects
Not sure about Clusters are
Noise and outliers All are the density
87 3 When is density based clustering preferred? All the number of irregular or
are present based clustering
clusters present intertwined
Euclidean distance
In the K-means clustering algorithm the distance
is the k-means
88 3 between cluster centroid to each object is Euclidean distance Cluster distance Cluster width None
clustering
calculated using ....method.
algorithm.
Partitioning is
Dynamic
Which technique finds the frequent itemsets in technique that
89 1 Partitioning Sampling Hashing itemset
just two database scans? finds the frequent
counting
itemsets
Finding of strong
Finding of strong
Using association to association rules
association rules Same as frequent
90 1 What is association rule mining? analyse correlation None using frequent
using frequent itemset mining
rules itemsets is an
itemsets
assoication rule.
An itemset which
An itemset which is is both closed and
An itemsetwhose no proper super-itemset has A frequent A closed itemsetA
91 1 both closed and None frequent are
same support is closed itemsets itemset closed itemset
frequent closed frequent
itemsets.
Apriori uses
Both apriori and Both apriori and Apriori uses Both apriori and
vertical and
FP-Growth uses FP-Growth uses horizontal and FP- FP-Growth uses
92 1 Which of the following is true? FP-Growth
horizontal data vertical data Growth uses vertical horizontal data
uses horizontal
format format data format format is true
data format
Support is
Some itemsets will Some itemsets will reduced by some
The number of
add to the current become infrequent itemsets will add
93 1 What will happen if support is reduced? frequent itemsets Can not say
set of frequent while others will to the current set
remains same
itemsets become frequent of frequent
itemsets
Support(A B) / Support(A B) / Support(A B) / Support(A B)
94 1 How do you calculate Confidence(A -> B)? None
Support (A) Support (B) Support (A) / Support (B)
The Apriori
If a rule is
If a rule is algorithm works
infrequent, its
What is the principle on which Apriori algorithm infrequent, its on if a rule is
95 1 generalized rules Both a and b None
work? specialized rules infrequent, its
are also
are also infrequent specialized rules
infrequent
are also infrequent
Apriori algorithm
It mines all It mines all
works on It mines
frequent patterns frequent patterns
None of the all frequent
96 1 What does Apriori algorithm through pruning through pruning Both a and b
above patterns through
rules with lesser rules with higher
pruning rules with
support support
lesser support
A frequent
A frequent A frequent A non-frequent itemsetwhose no
itemsetwhose no itemset whose itemset whose super-itemset is
97 2 What are maximal frequent itemsets? None
super-itemset is super-itemset is super-itemset is frequent is
frequent also frequent frequent maximal frequent
itemsets.
It mines
There are frequent It expands the
It expands the
chances that FP FP trees are very itemsets original database
98 2 What is not true about FP growth algorithms? original database
trees may not fit expensive to build . without to build FP trees
to build FP trees.
in the memory. candidate is not true
generation.
Decision trees is
Which of these is not a frequent pattern mining not a frequent
99 2 Decision trees FP growth Apriori Eclat
algorithm? pattern mining
algorithm
This clustering algorithm terminates when mean K-Means
values computed for the current iteration of the K-Means Conceptual Expectation Agglomerative clustering is the
100 2
algorithm are identical to the computed mean clustering clustering maximization clustering current iteration of
values for the previous iteration the algorithm.
Which of the following is not null invariant
lift is not null
101 2 measure(that does not considers null lift max_confidence cosine measure all_confidence
invariant measure
transactions)?
Absolute - Absolute -
Minimum support Minimum support
What is the difference between absolute and count threshold threshold and
102 2 Both mean same None None
relative support? and Relative - Relative -
Minimum support Minimum support
threshold count threshold
No we cannot use
Can FP growth algorithm be used if FP tree None of the
103 2 No Yes Both a and b FP growth
cannot be fit in memory? above
algorithm
An
An itemset for An itemsetwhose
An itemsetwhose An itemset for itemsetwhose
which at least no proper super-
no proper super- which at least no proper
104 2 What are closed itemsets? one proper itemset has same
itemset has same super-itemset has super-itemset
super-itemset has support is closed
support same confidence has same
same support itemsets
confidence
It mines all FP growth
It mines all It mines all frequent
frequent patterns algorithm do all
frequent patterns patterns through
105 2 What does FP growth algorithm do? through pruning All frequent patterns
by constructing a pruning rules with
rules with higher by constructing a
FP tree lesser support
support FP tree.
Number of
transactions
not containing
Support (A)
A Number of A / Total
means Number of
transactions Total Number of Total number of number of
transactions
106 2 What do you mean by support(A)? containing A / transactions not transactions transactions
containing A /
Total number of containing A containing Ans: Number
Total number of
transactions of transactions
transactions
containing A /
Total number
of transactions
Find all strong association rules given the support Cannot be
107 2 → I5, → → I5, → → I2 Null rule set None
is 0.6 and confidence is 0.8. determined
If it only satisfies If it satisfies both
There are
If it satisfies both min_support If it min_support and
When do you consider an association rule If it only satisfies other
108 3 min_support and satisfies both min_confidence
interesting? min_confidence measures to
min_confidence min_support and association rule
check so
min_confidence works
A frequent
itemset 'P' is a both are ture
When both a and b Support (P) = When a is true
109 3 When is sub-itemset pruning done? proper subset of when sub-itemset
is true Support(Q) and b is not
another frequent pruning is done
itemset 'Q'
Some association
rules will add to
Some association
Some association the current set of
Number of rules will become
What is the effect of reducing min confidence rules will add to association rules is
110 3 association rules invalid while others Can not say
criteria on the same? the current set of the effect of
remains same. might become a
association rules reducing min
rule.
confidence criteria
on the same
Market Basket
Analysis is direct
Which of the following is direct application of Market Basket Social Network Intrusion
111 3 Outlier Detection application of
frequent itemset mining? Analysis Analysis Detection
frequent itemset
mining.
Why is correlation analysis important?\nFor To weed out
To restrict the
questions given below consider the data To weed out To find large uninteresting
To make apriori number of
112 3 Transactions :\n1. I1, I2, I3, I4, I5, I6\n2. I7, I2, uninteresting number of frequent itemsets
memory efficient database
I3, I4, I5, I6\n3. I1, I8, I4, I5\n4. I1, I9, I10, I4, frequent itemsets interesting itemsets is correlation
iterations
I6\n5. I10, I2, I4, I11, I5 analysis
Apriori algorithm
Bottom-up and Top-down and Bottom-up and Top-down and works in bottom-
113 3 The apriori algorithm works in a ..and ..fashion?
breath-first breath-first depth-first depth-first up and breath-first
fashion.
FP growth
algorithm requires
114 3 Which algorithm requires fewer scans of data? FP growth Apriori Both a and b None
fewer scans of
data
115 3 Find odd man out: DBSCAN K mean PAM K medoid None
All techniques are
What techniques can be used to improve the Transaction Hash-based used to improve
116 3 All Partitioning
efficiency of apriori algorithm? Reduction techniques the efficiency of
apriori algorithm
Relation between
candidate and
A frequent itemset A candidate
What is the relation between candidate and No relation between frequent itemsets
117 3 must be a itemset is always Both are same
frequent itemsets? the two is frequent itemset
candidate itemset a frequent itemset
must be a
candidate itemset
Pattern evaluation
Measures to
measure are
What are Max_confidence, Cosine similarity, Pattern evaluation improve Frequent pattern
118 3 None Max_confidence,
All_confidence? measure efficiency of mining algorithms
Cosine similarity,
apriori
All_confidence
119 1 End Nodes are represented by __________ Triangles Squares Disks Circles None
Multivariate split is where the partitioning of
120 1 tuples is based on a combination of attributes "True" "False" None None None
rather than on a single attribute.
Unsupervised Supervised Reinforcement Missing data
121 1 Self-organizing maps are an example of None
learning learning learning imputation
Regression can
Assume you want to perform supervised learning
predict number of
and to predict number of newborns according to Structural
newborns
122 1 size of storks’ population Regression Classification Clustering equation
according to size
(http://www.brixtonhealth.com/storksBabies.pdf), modeling
of storks’
it is an example of
population
Some telecommunication company wants to Unsupervised
segment their customers into distinct groups to Unupervised Supervised learning is
123 1 Data extraction Serration
send appropriate subscription offers, this is an learning learning telecommunication
example of company
Decision Nodes are represented by
124 1 Squares Disks Circles Triangles None
____________
Outcome is the
In the example of predicting number of babies
example of
125 1 based on storks’ population size, number of Outcome Feature Attribute Observation
predicting
babies is
numbers.
126 1 Cost complexity pruning algorithm is used in? CART C4 ID3 All None
Attribute selection
Attribute selection measures are also known as measures are also
splitting rules. known as splitting
rules
By pruning the
Both By pruning the
longer rules you
How will you counter over-fitting in decision By pruning the By creating new longer rules’ and ‘ None of the
128 1 can counter over-
tree? longer rules rules By creating new options
fitting in decision
rules’
tree
Gain ratio tends to
prefer unbalanced
Gain ratio tends to prefer unbalanced splits in
splits in which one
129 1 which one partition is much smaller than the "True" "False" None None
partition is much
other.
smaller than the
other.
If...then... analysis
is the best suit the
Which of the following classifications would best
Market-basket Cluster student
130 2 suit the student performance classification If...then... analysis Regression analysis
analysis analysis performance
systems?
classification
systems
A _________ is a decision support tool that uses
Refer the
a tree-like graph or model of decisions and their Neural
131 2 Decision tree Graphs Trees definition of
possible consequences, including chance event Networks
Decision tree.
outcomes, resource costs, and utility.
CART is the cost
132 2 Cost complexity pruning algorithm is used in? CART C4.5 ID3 All
complexity used
Unsupervised
The problem of finding hidden structure in Unupervised Supervised Reinforcement Data
133 2 learning is
unlabeled data is called learning learning learning extraction
unlabeled data
You are given data about seismic activity in
Supervised Unsupervised Dimensionality
134 2 Japan, and you want to predict a magnitude of Serration None
learning learning reduction
the next earthquake, this is in an example of
Greedy approach
What is the approach of basic algorithm for is basic algorithm
135 2 Greedy Top Down Procedural Step by Step
decision tree induction? for decision tree
induction
Choose from the following that are Decision Tree Decision
136 2 All End Nodes Chance Nodes None
nodes? Nodes
In pre-pruning
A pruning set of The best pruned
a tree is
class labelled tree is the one that
'pruned' by All statements are
137 2 Which of the following sentences are true? All tuples is used to minimizes the
halting its true
estimate cost number of encoding
construction
complexity. bits.
early.
Data
Which of the following is not involve in data Knowledge Data Data transformation is
138 2 Data exploration
mining? extraction transformation archaeology not involved in
data mining
Gini index favour
139 2 Gini index does not favour equal sized partitions. "False" "True" None None equal sized
partitions
Structure in
Flow-Chart &
which internal
Structure in which
node represents
internal node
test on an
represents test on
attribute, each Refer the
an attribute, each
140 3 What is Decision Tree? branch Flow-Chart None definition of
branch represents
represents Decision tree.
outcome of test
outcome of test
and each leaf node
and each leaf
represents class
node represents
label
class label
Random
141 3 Which one of these is not a tree based learner? Bayesian classifier ID3 CART None
Forest
Task of inferring a
model from
Task of inferring a model from labeled training Supervised Unsupervised Reinforcement Complax labeled training
142 3
data is called learning learning learning learning data is called
Supervised
learning
Pessimistic Postpruning and
Cost complexity
Postpruning and pruning and None of the Prepruning are
143 3 What are two steps of tree pruning work? pruning and time
Prepruning Optimistic options two steps of tree
complexity pruning
pruning pruning.
Classifiers that
perform a series Classifiers which
of condition form a tree with Both are tree-
144 3 What are tree-based classifiers? Both None
checking with each attribute at one based classifiers
one attribute at a level
time
Random Forest is
Bayesian Belief
145 3 Which one of these is a tree based learner? Random Forest Bayesian classifier Rule based the tree-based
Network
leraner.
Use a white box Worst, best and
Possible
Which of the following are the advantage/s of model, If given expected values can
146 3 All Scenarios can None
Decision Trees? result is provided be determined for
be added
by a model different scenarios
When the number of classes is large Gini index is Gini index is not a
not a good choice. good choice
Discriminating between spam and ham e-mails is
148 3 "True" "False" None None None
a classification task, true or false?
Simple random Simple random
sampling of time Horizon parameter sampling of time
Three parameters
series is probably is the number of series is probably
149 1 Point out the wrong statement. are used for time All
the best way to consecutive values not the best way
series splitting
resample times in test set sample to resample times
series data. series data.
The cluster
sampling, stratified
sampling or
The cluster sampling, stratified sampling or Non random
150 1 Random sampling Indirect sampling Direct sampling systematic
systematic samplings are types of ________ sampling
samplings are
types of random
sampling.
createResample
Which of the following can be used to generate can be used to
151 1 balanced cross–validation groupings from a set of createFolds createSample createResample None make simple
data? bootstrap
samples.
The unknown or
exact value that
represents the
whole population
Which of the following is classified as unknown
is called as
152 1 or exact value that represents the whole Parameter Guider Predictor Estimator
parameter.
population?
Generally
parameters are
defined by small
Roman symbols.
PCA is a
technique for
reducing the
dimensionality of
Which of the following is NOT supervised Naive large datasets,
153 1 PCA Decision Tree Linear Regression
learning? Bayesian increasing
interpretability but
at the same time
minimizing
information loss.
In judgement
sampling is carried
under an opinion
of an expert. The
In which of the following types of sampling the
Judgement Convenience Quota judgement
154 1 information is carried out under the opinion of an Purposive sampling
sampling sampling sampling sampling often
expert?
results in a bias
because of the
variance in the
expert opinion.
There are many
Which of the following package tools are present Pre-
155 1 All Feature selection Model tuning different modeling
in caret? processing
functions in R.
Which of the following can be used to create
Splitting is based
156 1 sub–samples using a maximum dissimilarity maxDissim minDissim inmaxDissim All
on the predictors.
approach?
Factors that affect
the performance
Which of the factors affect the performance of Good data Representation of learner system
157 2 Training scenario Type of feedback
learner system does not include? structures scheme used does not include
good data
structures.
If the argument to
this function is a
factor, the random
sampling occurs
Which of the following function can be used to within each class
158 2 createDataPartition newDataPartition renameDataPartition None
create balanced splits of the data? and should
preserve the
overall class
distribution of the
data.
In language
understanding, the
levels of
In language understanding, the levels of
159 2 Empirical Syntactic Phonological Logical knowledge that do
knowledge that does not include?
not include
empirical
knowledge.
Rolling forecasting
origin techniques
Which of the following function can create the
160 2 createTimeSlices newTimeSlices binTimeSlices None are associated
indices for time series type of splitting?
with time series
type of splitting.
In Cluster the
population is
divided into
various groups
The selected clusters in a clustering sampling are Proportional called as clusters.
161 2 Elementary units Primary units Secondary units
known as ________ units The selected
clusters in a
sample are called
as elementary
units.
p → Øq is not a
162 2 Among the following which is not a horn clause? p → Øq Øp V q p→q p
horn clause.
Entropy is a
measure of the
randomness in the
information being
processed. The
higher the entropy,
the harder it is to
High entropy means that the partitions in
163 2 Not pure Pure Useful Useless draw any
classification are
conclusions from
that
information.\nIt is
a measure of
disorder or purity
or unpredictability
or uncertainty.\n
Generally a
sample having 30
or more sample
values is called a
A sample size is considered large in which of the large sample. By
164 2 n > or = 30 n > or = 50 n < or = 30 n < or = 50
following cases? the Central Limit
Theorem such a
sample follows a
Normal
Distribution.
The method of
selecting a
desirable portion
from a population
The method of selecting a desirable portion from
that describes the
165 2 a population which describes the characteristics Sampling Segregating Dividing Implanting
characteristics of
of whole population is called as ________
the whole
population is
called as
Sampling.
Attributes are
statistically
dependent of one
Attributes are Attributes are
another given the
statistically Attributes are statistically Attributes can
Which of the following statements about Naive class value
166 2 dependent of one equally independent of one be nominal or
Bayes is incorrect? Attributes are
another given the important. another given the numeric
statistically
class value. class value.
independent of
one another given
the class value.
Sampling error is
inversely
proportional to the
Sampling error increases as we increase the sampling size. As
167 2 "False" "True" None None
sampling size. the sampling size
increases the
sampling error
decreases.
The function
dummyVars takes
The function
a formula and a
Caret includes dummyVars can be
Asymptotics data set and
several functions used to generate a
are used for outputs an object
168 2 Point out the correct statement. All to pre-process complete set of
inference that can be used
the predictor dummy variables
usually to create the
data from one or more
dummy variables
factors
using the predict
method.
In a sampling
distribution the
mean of the
population is equal
to the mean of the
If the mean of population is 29 then the mean of sampling
169 2 29 30 21 31
sampling distribution is __________ distribution.
Hence mean of
population=29.
Hence mean of
sampling
distribution=29.
The caret package
is a set of
functions that
Caret stands for classification and regression attempt to
training. streamline the
process for
creating predictive
models.
Caret uses the
171 3 Caret does not use the proxy package. "False" "True" None None
proxy package.
A model of
language consists
A model of language consists of the categories Role structure of of the categories
172 3 Structural units System constraints Language units
which does not include? units which does not
include structural
units.
Study of
population is
called a Census.
Suppose we want to make a voters list for the
Hence for making
173 3 general elections 2019 then we require Census Sampling error Random error Simple error
a voter list for the
__________
general elections
2019 we require
Census.
Different learning
methods does not
174 3 Different learning methods does not include? Introduction Analogy Deduction Memorization
include the
introduction.
The density-based
clustering methods
recognize clusters
based on the
density function
Suppose we would like to perform clustering on
distribution of the
spatial data such as the geometrical locations of
Density-based Model-based K-means data object. For
175 3 houses. We wish to produce clusters of many Decision Trees
clustering clustering clustering clusters with
different sizes and shapes. Which of the following
arbitrary shapes,
methods is the most appropriate?
these algorithms
connect regions
with sufficiently
high densities into
clusters.
sumDiss can be
Which of the following function can be used to used to maximize
176 3 All minDiss avgDiss sumDiss
maximize the minimum dissimilarities? the total
dissimilarities.
In sampling
distribution the
parameter k
represents
In sampling distribution what does the parameter Secondary Sub stage
177 3 Sampling interval Multi stage interval Sampling interval.
k represents ________ interval interval
It represents the
distance between
which data is
taken.
Maximum
possible different
A machine learning problem involves four examples are the
attributes plus a class. The attributes have 3, 2, 2, products of the
178 3 and 2 possible values each. The class has 3 72 24 48 12 possible values of
possible values. How many maximum possible each attribute and
different examples are there? the number of
classes;\n3 * 2 *
2 * 2 * 3 = 72\n
1Data selection is:
A. The actual discovery phase of a knowledge discovery process
B. The stage of selecting the right data for a KDD process
C. A subject-oriented integrated time variant non-volatile collection of data in support of management
D. None of these
Answer: B
2Discovery is:
A. It is hidden within a database and can only be recovered if one is given certain clues (an example IS
encrypted information).
B. The process of executing implicit previously unknown and potentially useful information from data
C. An extremely complex molecule that occurs in human chromosomes and that carries genetic information
in the form of genes.
D. None of these
Answer: B
3Data mining is:

A. The actual discovery phase of a knowledge discovery process
B. The stage of selecting the right data for a KDD process
C. A subject-oriented integrated time variant non-volatile collection of data in support of management
D. None of these
Answer: A
4Knowledge engineering is:

A. The process of finding the right formal representation of a certain body of knowledge in order to
represent it in a knowledge-based system
B. It automatically maps an external signal space into a system's internal representational space. They are
useful in the performance of classification tasks.
C. A process where an individual learns how to carry out a certain task when making a transition from a
situation in which the task cannot be carried out to a situation in which the same task under the same
circumstances can be carried out.
D. None of these
Answer: A
5KDD (Knowledge Discovery in Databases) is referred to:

A. Non-trivial extraction of implicit previously unknown and potentially useful information from data
B. Set of columns in a database table that can be used to identify each record within this table uniquely.
C. collection of interesting and useful patterns in a database
D. none of these
6Knowledge is referred to:

A. Non-trivial extraction of implicit previously unknown and potentially useful information from data
B. Set of columns in a database table that can be used to identify each record within this table uniquely
C. collection of interesting and useful patterns in a database
D. none of these
Answer: C
7Operational database is:

A. A measure of the desired maximal complexity of data mining algorithms
B. A database containing volatile data used for the daily operation of an organization
C. Relational database management system
D. None of these
Answer: B
8Which of the following is not a data mining functionality?

A. Characterization and Discrimination
B. Classification and regression
C. Selection and interpretation
D. Clustering and Analysis
Answer: C
9The various aspects of data mining methodologies is/are ......

i. Mining various and new kinds of knowledge
ii. Mining knowledge in multidimensional space
iii. Pattern evaluation and pattern or constraint-guided mining.
iv) Handling uncertainty, noise, or incompleteness of data
10The full form of KDD is ........

A. Knowledge Database
B. Knowledge Discovery Database
C. Knowledge Data House
D. Knowledge Data Definition
Answer: B
11The output of KDD is ..........

A. Data
B. Information
C. Query
D. Useful information/Knowledge
Answer: D
12The process of removing the deficiencies and loopholes in the data is called as
A. Aggregation of data
B. Extracting of data
C. Cleaning up of data.
D. Loading of data
Answer: C
13Which of the following process includes data cleaning, data integration, data selection, data
transformation, data mining, pattern evolution and knowledge presentation?
A. KDD process
B. ETL process
C. KTL process
D. MDX process
Answer: A
14Data mining application domains are

A. Biomedical
B. DNA data analysis
C. Financial data analysis
D. Retail industry and telecommunication industry
E. All (a), (b), (c) and (d) above.
Answer: E
15Which of the following is/are the Data mining tasks?

A. Regression
B. Classification
C. Clustering
D. inference of associative rules
E. All (a), (b), (c) and (d) above.
Answer: E
16Which of the following is not an ETL tool?

A. Informatica
B. Oracle warehouse builder
C. Datastage
D. Visual studio
Answer: D
17______ is not a data mining functionality?

A. Clustering and Analysis
B. Selection and interpretation
C. Classification and regression
D. Characterization and Discrimination
ANSWER: B
18To remove noise and inconsistent data ____ is needed.
(A)
Data Cleaning
(B)
Data Transformation
(C)
Data Reduction
(D)
Data Integration
Answer:A
19Multiple data sources may be combined is called as _____
(A)
Data Reduction
(B)
Data Cleaning
(C)
Data Integration
(D)
Data Transformation
Answer:C
20What is the use of data cleaning?
A. to remove the noisy data

B. correct the inconsistencies in data
C. transformations to correct the wrong data.
D. All of the above
Answer:D
21Data set {brown, black, blue, green , red} is example of Select one:
A. Continuous attribute
B. Ordinal attribute
C. Numeric attribute
D. Nominal attribute
Answer:D
22Binary attribute are
A.
This takes only two values. In general, these values will be 0 and 1 and .they can be coded as one bit
B.
The natural environment of a certain species
C.
Systems that can be used without knowledge of internal operations
D.
None of these
Answer:A
23Euclidean distance measure is
A.
A stage of the KDD process in which new data is added to the existing selection.
B.
The process of finding a solution for a problem simply by enumerating all possible solutions according to
some pre-defined order and then testing them
C.
The distance between two points as calculated using the Pythagoras theorem
D.None of These
24If there is a very strong correlation between two variables then the correlation coefficient must be
a. any value larger than 1
b. much smaller than 0, if the correlation is negative
c. much larger than 0, regardless of whether the correlation is negative or positive
d. None of these alternatives is correct.
Answer:B
Which of the following is a good alternative to the star schema?
A. Snowflake schema
B. Star schema
C. Star snowflake schema
D. Fact constellation
ANSWER: D
Patterns that can be discovered from a given database are which type
A. More than one type
B. Multiple types always
C. One type only
D. No specific type
ANSWER: A
A star schema has what type of relationship between a dimension and

fact table?
A. Many-to-many
B. One-to-one
C. One-to-many
ANSWER: C
A snowflake schema is which of the following types of tables?

A. Fact
B. Dimension
C. Helper
D. All of the above
ANSWER: D
Euclidean distance measure is

A. A stage of the KDD process in which new data is added to the
existing selection.
B. The process of finding a solution for a problem simply by
enumerating all possible solutions according to some pre-defined
order and then testing them
C. The distance between two points as calculated using the
Pythagoras theorem
D. None of these
ANSWER: C
Which one manages both current and historic transactions?

A. OLTP
B. OLAP
C. Spread sheet
D. XML
Answer: B
The data Warehouse is__________.

A. ReadOnly
B. WriteOnly
C. Read and write only
D. None of these
ANSWER: A
Expansion for DSS in DW is__________.
A. Decision Support system
B. Decision Single System
C. Data Storable System
D. Data support system
ANSWER: A
The time horizon in Data warehouse is usually __________.

A. 1-2 years
B. 3-4 years
C. 5-6 years
D. 5-10 years
ANSWER: D
__________describes the data contained in the data warehouse

A. Relational data
B. Operational Data
C. Meta Data
D. Informational Data
ANSWER: C
Treating incorrect or missing data is called as ___________.

A. Selection.
B. Preprocessing
C. Transformation
D. Interpretation
ANSWER: B
Converting data from different sources into a common format for

processing is called as________.
A. Selection.
B. Preprocessing
C. Transformation
D. Interpretation
ANSWER: C
Which is not a property of data warehouse?

A. Subject oriented
B. Time varient
C. Volatile
D. collection from heterogeneous sources
ANSWER: C
Data warehousing is used in_______________

A. Transaction System
B. Database management system
C. Decision support system
D. Expert system
ANSWER: C
What are the characeristics of OLAP systems?

A. Query driven
B. More users
C. Integrated
D. Store current data
ANSWER: C
Data warehouse is based on_____________

A. two dimensional model
B. three dimensional model
C. Multi dimensional model
D. Unidimensional model
ANSWER: C
Data warehousing is related to______

A. delete data
B. Update data
C. Write new data
D. scan and load data for analysis
ANSWER: D
Multidimensional model of data warehouse called as_____

A. data structure
B. table
C. tree
D. data cube
ANSWER: D
OLAP usage is____

A. Repetative
B. Adhoc
C. Frequently
D. Daily
ANSWER: B
In data warehousing what is time-variant data?

A. Data in the warehouse is only accurate and valid at some point in
time or over time interval
B. Data in the warehouse is always accurate and valid
C. Data in the warehouse is not accurate
D. Data in the warehouse is only accurate sometimes
ANSWER: A
Is the data in a data warehouse generally updated in real-time?

A. YES
B. NO
ANSWER: B
What is a Star Schema?

A. A star schema consists of a fact table with a single table for
each dimension
B. A star schema is a type of database system
C. A star schema is used when exporting data from the database
D. None of these
ANSWER: A
What is a Snowflake Schema?

A. Each dimension table is normalized, which may create additional
tables attached to the dimension tables
B. A Snowflake schema is a type of database system
C. A Snowflake schema is used when exporting data from the database
D. None of these
ANSWER: A
What does the acronym ETL stands for?

A. Explain,Transfer and Lead
B. Extract,Transform and Load
C. Extract,Transfer and Load
D. Effect,Transfer and Load
ANSWER: B
What is the system of data warehousing mostly used for?

A. Data integration and Data Mining
B. Data Mining and Data Storage
C. Reporting and Data Analysis
D. Data Cleaning and Data Storage
ANSWER: C
Which small logical units do data warehouses hold large amounts of

information?
A. Data Storage
B. Data Marts
C. Access layers
D. Data Miners
ANSWER: B
Why do we need ODS?

A. To update data periodically
B. To prepare data for ETL
C. To back up data
D. To prepare data for regression
ANSWER: B
Which one is correct for data warehousing?

A. It can be updated by end users
B. It can solve all business questions
C. It is designed for focus subject areas
D. It contains only current data
ANSWER: C
Why do we apply in snowflake schema?

A. Aggregation
B. Normalization
C. Specialization
D. Generalization
ANSWER: B
The data collected in data warehouse can be used for analyzing

purposes.
A. TRUE
B. FALSE
ANSWER: A
A snowflake schema is a normalized star schema
A. TRUE
B. FALSE
ANSWER: A
A fact table is related to dimensional table as a ___ relationship

A. 1:M
B. M:N
C. M:1
D. 1:1
ANSWER: C
Data warehouse contains_____________data that is never found in the

operational environment
A. normalized.
B. Informational
C. Summary
D. Denormalized
ANSWER: C
Identify correct type of attribute.
A. nominal
B. binary
C. ordinal
D. All of these
ANSWER: D
Minkowski distance is a function used to find the distance between

two
A. Binary vectors
B. Boolean-valued vectors
C. Real-valued vectors
D. Categorical vectors
ANSWER: C
Which distance measure is similar to Simple Matching Coefficient

(SMC)?
A. Euclidean
B. Hamming
C. Jaccard
D. Manhattan
ANSWER: B
Data set of designation {Professor, Assistant Professor, Associate

Professor} is example of__________attribute.
A. Continuous
B. Ordinal
C. Numeric
D. Nominal
ANSWER: D
Identify correct example of ordinal attributes?

A. Price of product
B. Age of person
C. Car colors
D. Students Grade
ANSWER: D
Identify the correct example of Nominal Attributes.

A. Weight of person in Kg
B. Income categories - HIGH, MEDIUM, LOW
C. Mobile number
D. All above
ANSWER: B
Consider the two objects i and j with nominal attributes, the

dissimilarity between these objects are calculated using below
equation:
d(i,j)= (p-m)/p. In this formula what p and m represents?
A. m is the number of matches, p is the total number of rows in
the dataset
B. m is the number of matches, p is the total number of
variables/features
C. m is the matrix, p is the total number of variables/features
D. All are wrong
ANSWER: B
When objects are represented using single attribute, the proximity

value 1 indicates :
A. Objects are similar
B. Objects are dissimilar
C. Not equal
D. Reflexive
ANSWER: A
The name of the table used for measuring similarity between objects
represenred using 2 or more binary attributes is:
A. Sqaure Matrix
B. Contegency Table
C. Triangular Matrix
D. None of the above
ANSWER: B
Gender is the example of Asymmetric Binary Attribute.

A. TRUE
B. FALSE
ANSWER: B
Identity correct equation of Jacard Coefficient:

A. J= f11/f01+f10+f11
B. J= f11+f00/f01+f10+f11
C.J= f11+f00/f01+f10
D. None of these
ANSWER: A
If distance d is given we can calculate similarity using equation s=

d-1. (True/ False)
A. True
B. False
ANSWER: A
What equation we get when r parameter =2 in Minskowski Distance

formula?
A. Manhattan distance
B. Euclidean distance
C. LMaximum Distance
D. All
ANSWER: B
Identify the distance measure to calculate distance between two

objects:
A. Manhattan
B. L2
C. L1
D. Contgency Matrix
ANSWER: A
________is a generalization of Manhattan, Euclidean and Max Distance

A. Euclidean Distance
B. Minkowski Distance
C. Manhattan distance
D. Jaccard Distance
ANSWER: B
______ distance is based on L2 norm.

D. Jaccard Distance
ANSWER: A
_________ distance is based on L1 norm.

D. Jaccard Distance
ANSWER: C
_________ refers to a similarity or dissimilarity

A. Distance
B. Proximity
C. Enclidean
D. Manhattan
ANSWER: B
Which is not the type of attribute used in distance measure?

A. Ordinal
B. Nominal
C. Binay
D. Rank
ANSWER: D
_____ method is used to find the distance between two objects

represented by Nominal attributes.
D. Simple Matching
ANSWER: D

represented by numerical attributes.
D. All of these
ANSWER: D

represented by Binary attributes.
D. Jaccard coefficient
ANSWER: D
Contingency table is prepared for _______ attribute data.

A. Ordinal
B. Nominal
C. Binay
D. Integer
ANSWER: C
Which is not the property of distance?

A. Distance is nonnegative number
B. Distance of an object to itself is 0
C. Distance is a symmetric function
D. Distance is negative number
ANSWER: D
If d1 and d2 are two vectors, identify correct equation of cosine

similarity.
A. Cos(d1, d2)= (d1.d2)/ ||d1|| ||d2||
B. Cos(d1, d2)= |d1|| ||d2|| / (d1.d2)
C. Cos(d1, d2)= (d1.d2)
D. Cos(d1, d2)= (d1.d2)/ ||d1||
ANSWER: A
Which are the applications of proximity measures?

A. Classification
B. Clustering
C. KNN classifier
D. All of these
ANSWER: D
If o1 and o2 are two objects and distance between these objects is 1

then o1 and o2 are totally similar (True/false)
A. True
B. False
ANSWER: B

then o1 and o2 are totally dissimilar (True/false)
A. True
B. False
ANSWER: A
_________ matrix represents the distance between all objects in the

dataset
A. Confusion
B. Dissimilarity
C. Similarity
D. Square
ANSWER: B

then it means_____
A. o1 and o2 are totally similar
B. o1 and o2 are totally dissimilar
C. o1 and o2 are similar
D. o1 and o2 are partially dissimilar
ANSWER: B
If o1 and o2 are two objects and distance between these objects is

zero then o1 and o2 are totally dissimilar (True/false)
A. True
B. False
ANSWER: B

zero then it means_____
A. o1 and o2 are totally similar
B. o1 and o2 are totally dissimilar
C. o1 and o2 are similar
D. o1 and o2 are partially dissimilar
ANSWER: A

zero then o1 and o2 are totally similar (True/false)
A. True
B. False
ANSWER: A
Identify the correct subtype of Binary attribute.

A. Ordinal
B. Asymmetric
C. Symmetric
D. Both B and C
ANSWER: D
______ Is higher when objects are more alike

A. Dissimilarity
B. Distance
C. Similarity
D. Accuracy
ANSWER: C
_____ Lower when objects are more alike.

A. Dissimilarity
B. Recall
C. Similarity
D. Accuracy
ANSWER: A
MCQ
SUBJECT: DATA MINING AND WAREHOUSING
UNIT-I
1. ________ is as finding hidden information in a database.

a) Data mining
b) Database access
c) DBMS
d) Data warehouse.
2. KDD means ___________ discovery in databases.
a) King
b) Kite
c) Knowledge
d) Kind
3. ___________ model makes a prediction about values of data using known results found from
different data.
a) Descriptive
b) Preference
c) Predictive
d) Algorithm
4. ___________ maps data into predefined grouped or classes.
a) Classification
b) Regression
c) Prediction
d) Summarization
5. __________ model identifies patterns or relationships in data.
a) Predictive
b) Non-predictive
c) Descriptive
d) Unpredictable
6. ___________ is he use of algorithm to extract the information and patterns derived by the KDD
process.
a) Data mining
b) Data base
c) Data access
d) Data processing
7. ________ is he process of finding useful information and paterns in data.
a) Data mining
b) KDD
c) Data warehouse
d) Data processing
8. __________ is a type of classification where an input pattern is classified into one of several
classes based on predefined classes
a) Pattern recognition
b) TSA
c) Clustering
P.ARAVINDAN MCA, M.PHIL.

d) Prediction
9. _________is used to map data item into real valued prediction variable.
a) Clustering
b) Classification
c) Regression
d) TSA
10. ___________ is used to visualize the time series.
a) Time series plot
b) Watch dog
c) Time series analysis
d) Grouping
11. Clustering is also called as ____________.
a) Grouping
b) Segmentation
c) Unsupervised learning
d) All the above
12. Summarization is also called as______________.
a) Characterization
b) Generalization
c) Simple description
d) All the above
13. _________ maps data into sunsets with associated simple description .
a) Summarization
b) Association Rules
c) Classification
d) Clustering
14. __________ refers to the DM task of uncovering relationships among data.
a) Link analysis
b) Clustering
c) TSA
d) Summarization
15. __________ is a model that identifies specific types of data association.
a) TSA
b) Sequence discovery
c) Clustering
d) Association Rules
16. __________ is used to determine sequential patterns in data.
a) TSA
b) Sequence discovery
c) Clustering
d) Association rules
17. The definition of KDD includes the keyword __________.

a) Useful
b) This
c) DM
d) All the above

18. In transformation ____________ is used to reduce the number of possible data values being
considered.
a) Data reduction
b) Data interchange
c) Errorneous of data
d) Clearence of data
19. ____________ techniques are used to make the data easier to mine and more useful and to
provide meaningful results.
a) Preprocessing
b) Selection
c) Transformation
d) Interpretation
20. __________ refers to the visual representation of data.
a) GUI
b) Interpretation
c) Visualization
d) Hybrid
21. _______ techniques include the box plot and scatter diagram.
a) Graphical
b) Geometric
c) Icon-based
d) Pixel-based
22. __________ is used to proceed from specific knowledge to more general information.
a) Compression
b) Induction
c) Hybrid
d) Pruning
23. ____________ occurs when the model does not fit future states.
a) Overfitting
b) Human interaction
c) Outliers
d) Integration
24. There are many data entries that do not fit nicely into derived model.
a) Overfitting
c) Outliers
d) Integration
25. IR stands for____________.
a) Information reduction
b) Information retrieval
c) Information results
d) Information relation
26. __________ is a software that is used to access the database.
a) DBMS
b) OLTP
c) SQL
d) CFMS

27. __________ data is said to be invalid or incorrect.
a) Missing data
b) Irrelevant data
c) Noisy data
d) Changing data
28. ROI stands for _______________.
a) Return on investment
b) Return on instruction
c) Return on information
d) Return on invalid data
29. The use of other attributes that increase the complexity and decrease in algorithm is called
_____________.
a) Dimensionality Curse
b) Dimensionality reduction
c) Dimensionality attribute
d) Dimensionality
30. __________ techniques are targeted to such application as fraud detection, criminal suspects,
prediction of terrorist.
a) DM
b) DB
c) DBMS
d) OLTP
31. ___________ access a database using a well defined query stated in language such as SQL.
a) DBMS
b) DBS
c) KDD
d) Database queries
32. A database is partitioned into disjoint grouping of similar tuples called __________.
a) Clustering
b) Classification
c) Segmentation
d) Generlization
33. __________ finds occurrences of a predefined pattern in data.
a) Patterning
b) Pattern recognition
c) Patterning of data
d) Pattern analysis
34. In KDD, the input to the process is known as _______ and the Output is ________.
a) Informtion , data
b) Field,record
c) Record,field
d) Data ,information
35. In KDD,obtaining the data from various DB, files,and other sources is called ______.
a) Preprocessing
b) Selection
c) Tranformation
d) Evaluation

36. Link analysis is otherwise called as_________.
a) Association
b) Association rule
c) Affinity analysis
d) All the above
37. Prediction application include ___________.
a) Flooding
b) Speech recognition
c) Machine learning
d) All the above
38. In regression, some type of error analysis is used to determine which function is____.
a) Good
b) Best
c) Excellent
d) Bad
39. Data mining is otherwise called as_______________.
a) Data analysis
b) Data discovery
c) Deductive learning
d) All the above
40. The rise of DBMS tool is________.
a) 1960
b) 1970
c) 1980
d) 1990
41. The metrics used include the traditional metrics of space and time based on _________.
a) Complexity analysis
b) Effectiveness
c) Usefulness of data
d) Scalability
42. ____________ data are noisy and have many missing attributes values.
a) Real world
b) Abstract
c) Assumption
d) Authorized
43. The use of ________ data is found in GIS data base .
a) Missing
b) Irrelevant
c) Noisy
d) Multimedia
44. A large DB can be viewed as using___________ to help uncover hidden information about the
data.
a) Search
b) Compression

c) Approximation
d) Querying
45. Interfaces between technical experts and domain comes under______ issues.
a) Overfitting
c) Outlier
d) Application
46. The data Mining process can itself be vies a type of _____ underlying database.
a) Querying
b) Induction
c) Search
d) Processing
47. ___ requests may be treated as special,unusual or one time needs.
a) KDD
b) DM
c) DBMS
d) DB
48. ______ and___________ are effective tools to attack scalability problems.
a) Dimensionality & Parallelization
b) Sampling &Dimensionality
c) Effectiveness &Sampling
d) Sampling & Parallelization
49. Large data set is otherwise called as ________.
a) Massive datasets
b) High datasets
c) Noisy datasets
d) Irrelevent datasets
50. KDD process consists of _________ steps .
a) One
b) Three
c) Four
d) Five

UNIT-II
51. ________ models describe the relationship between I/O through algebraic equation.
a) Parametric
b) Non-parametric
c) Static
d) Dynamic
52. _______ may also be used to estimate error.
a) Squared error
b) Root mean error
c) Mean Root square
d) Mean squared error
53. _________ assumes that a linear relationship exists between the input data and the output data.
a) Bivariate regression
b) Correlation
c) Multiple regression
d) Linear regression
54. The _________ algorithm solves the estimation problem with incomplete data.
a) Expectation maximization
b) Expectation minimization
c) Summarization-maximization
d) Summarization minimization
55. Decision tree uses a _________ techniques.
a) Greedy
b) Divide & Conquer
c) Shortest Path
d) BFS
56. Null hypothesis and _______ hypothesis are two complementary hypothesis.
a) Classical
b) Testing
c) Alternative
57. The BIAS of an estimator is the difference between ______ & _______values.
a) Expected,actual
b) Actual ,Expected
c) Maximal,Minimal
d) Minimal,Maximal
58. An __________ estimator is one whose BIAS is 0.
a) Unbiased
b) Rule biased
c) Mean Root square
d) Mean squared error

59. ________ is defined as the expected value of the squared difference between the estimate and the
actual value.
a) MSE
b) RMS
c) EM
d) MLE
60. The________ may also be used to estimate error or another statistic to describe a distribution.
a) RMS
b) MLE
c) EM
d) MSE
61. _______ is a technique to estimate the likelihood of a property given the set of data as evidence
or input.
a) Point Estimation
b) Models based on summarization
c) Bayes theorem
d) Hypothesis testing
62. In Box plot the Total range of the data value is divided into ________.
a) Regions
b) Quartiles
c) Divisions
d) Partitions
63. ________ measure is used instead of similarity measures.
a) Distance
b) Dissimilarity
c) Both a,b
64. _________ relates the overlap to the average size of the two sets together.
a) Dice
b) Jaccard
c) Cosine
d) Overlap
65. ________ is used to measure the overlap of two sets as related to the whole set caused by their
union.
a) Dice
b) Jaccard
c) Cosine
d) Overlap
66. ________ coefficient relates the overlap to the geometric average of the two sets.
a) Dice
b) Jaccard
c) Cosine
d) Overlap

67. The_________ metrics determines the degree to which the two sets overlap.
a) Dice
b) Jaccard
c) Cosine
d) Overlap
68. ________ is a predictive modeling technique used in classification ,clustering,etc.

a) Neural networks
b) Decision tree
c) Genetic algorithm
d) All the above
69. The neural networks can be viewed as a directed graph with __________ nodes.
a) Two
b) Three
c) Four
d) One
70. Internal nodes are also called as _________.
a) Input
b) Output
c) Hidden
d) Sink
71. In neural networks _______ activation function produces a linear output value based on the input.
a) Threshold
b) Step
c) Linear
d) Sigmoid
72. ______ is a bell shaped curve with output values in the range [0,1].
a) Linear
b) Guassian
c) Hyperbolic
d) Sigmoid
73. In neural network , ___________ is an S shaped curve with output values -1,1
a) Sigmoid
b) Linear
c) Step
d) Hyperbolic
74. The crossover technique generates new individual called________.
a) Offspring
b) Children
c) Both a, b
75. _______ is used to determine the best individuals in a population.
a) Crossover
b) Mutation
c) Fitness function
d) All the above

76. The______________ operation randomly changes character in the offspring.
a) Crossover
b) Mutation
c) Fitness function
d) Both a,b
77. __________ is defined by precise algorithms that indicate how to combine the given set of
individual to produce new ones.
a) Production
b) Reproduction
c) Genetic algorithms
d) Crossover
78. The activation function is also called as____________.
a) Processing element function
b) Squashing function
c) Firing rule
d) All the above
79. The subsections of the chromosomes are called___________.
a) Cross over
b) Genes
c) Alleles
d) Offspring
80. ________ is used to estimate error or to describe a distribution.
a) RMS
b) MSE
c) SE
d) Jackknife
81. ________ can be defined as a value proportional to actual probability with specific distribution.
a) Likelihood
b) Maximum Likelihood
c) Estimation
82. In hypothesis testing O represents _____________.
a) Outliers
b) Observed data
c) Output
83. One standard formula to measure linear correlation is the ____________.
a) Correlation coefficient
b) Classification
c) Clustering
d) Dissimilarity measures
84. _________ are often used instead o similarity measures.
a) Distance
b) Dissimilarity measure
c) Both a,b

85. A variation of sigmoid function is called___________.
a) Gaussian
b) Hyperbolic
c) Linear
d) Threshold
86. Gaussian function is a ___________ shaped curve.
a) S
b) V
c) Bell
d) C
87. ________ is used to determine the best individuals in a population.
a) Mutation
b) Fitness function
c) Crossover
d) Starting set
88. One of the most important components of a genetic algorithm is__________.
a) How to select individual
b) How to select offspring
c) How to select crossover
d) How to select fitness
89. _________ coefficient is used to measure the overlap of two sets as related to whole set caused
by their union.
a) Dice
b) Jaccard
c) Cosine
d) Overlap
90. _______ coefficient is used to relates the overlap to the average size of two sets together.
a) Dice
b) Jaccard
c) Cosine
d) Overlap
91. _______ coefficient relates the overlap to the geometric average of the two sets.
a) Dice
b) Jaccard
c) Cosine
d) Overlap
92. The_______ metric determines the degree to which the two sets overlap.
a) Overlap
b) Dice
c) Cosine
d) Jaccard
93. Rejection of null hypothesis causes another hypothesis called__________ hypothesis.
a) Alternative
b) Similarity measure
c) Correlation
d) Mutation

94. The input nodes exist in ___________ layer.
a) Output
b) Input
c) Hidden
d) All the above
95. Internal nodes is called _________ nodes.
a) Input
b) Output
c) Hidden
d) All the above
96. Artificial NNs can be classified based on the type of_____________.
a) Connectivity
b) Learning
c) Both a, b
97. ________ occurs when the NNs is trained to fit one set to data.
a) Outlier
b) Noisy data
c) Missing data
d) Overfitting
98. To avoid overfitting _______ NNs are advisable.
a) Larger
b) Smaller
c) Medium
d) All the above
99. In sigmoid , c is a _____________.
a) Change
b) Constant
c) Crossover
d) Children
100. ____ is defined as the excepted value of the squared difference between the estimate and the
actual value.
a) MSE
b) RMSE
c) BIAS
d) RMS

UNIT-III
101. Estimation and prediction may be viewed as types of _____________.
a) Clustering
b) Classification
c) Regression
d) Time Series
102. Classification performed by dividing the input space of potential database tuples into _______.
a) Regions
b) Class
c) Space
d) Sector
103. ________ values cause during both training and the classification process itself.
a) Data
b) Class
c) Predicate
d) Missing data
104. The performance of classification usually examined by evaluating the ___of the classification.
a) Accuracy
b) Contribution
c) Special value
d) Missing values
105. Classification true positives and false positives are calculated by the following curve.
a) MOC
b) NOC
c) ROC
d) COC
106. The __________ matrix illustrates the accuracy of the solution to a classification problem.
a) Confusion
b) Mutation
c) Crossover
d) Gaussian
107. ______ problems deal with estimation of an output value based on input values.
a) Prediction
b) Classification
c) Clustering
d) Regression

108. _____ is erroneous data.
a) OC
b) Regression
c) Noise
d) Linear model
109. Which are data values that are exceptions to the usual and expected data?
a) Outliers
b) Noise
c) Regression
d) Poor fit
110. The _______ classification can be viewed as both a descriptive and a predictive type of
algorithm.
a) Naive
b) Bayes
c) Naive bayes
d) Prediction
111. The similarity (or) distance measures may be used to identify the _____ of different items in the
database.
a) Likeness
b) Alikeness
c) Outliers
d) Centroid
112. A straightforward distance based approach assuming the each class Ci is represented by__.
a) Centroid
b) Outlier
c) Medoid
d) KNN
113. Expand : KNN
a) K Normal Neighbors
b) K Nearest Neighbor
c) K Normal Nextvalue
d) K Nearest Nest
114. The decision tree approach to classification is to divide search space into _______ regions.
a) Square
b) Triangular
c) Circular
d) Rectangular

115. In DT ,each internal node is labled with an _______.
a) Class
b) Attribute
c) Arc
d) Database
116. In DT, each leaf node labled with ____.
a) Class
b) Attribute
c) Arc
d) Link
117. The _____ technique to building a DT is based on information theory and attempts to minimize
the expected number of comparisons.
a) CART
b) ID3
c) C.4.5
d) ROC
118. Neural networks are more robust than DTs because of the _________.
a) Arcs
b) Links
c) Weights
d) Classes
119. In NN, the normal approach used for processing is called________.
a) Activation function
b) Interconnections
c) Training data
d) Propagation
120. The NN starting state is modified based on feedback of its performance is referred to as__.
a) Supervised
b) Unsupervised
c) Both (a) and (b)
d) None of these
121. ________ learning can also be performed if the output is not known.
a) Supervised
b) Unsupervised
c) Neither (a) or (b)
d) Oral

122. The Mean Squared Error (MSE) is found by ________.
a) (yi-di)2/2
b) (yi+di)2/2
c) (di-yi)2/2
d) (di+yi)2/2
123. The ____ can be used to find a total error over all nodes in the network.
a) RDF
b) ROC
c) MSE
d) CMC
124. Which learning technique that adjusts weights in the NN by propagating weight changes
backward from the sink to the source nodes?
a) Propagation
b) perceptrons
c) MSE
d) Back propagation
125. In radial basis function (RBF) central point value is ______.
a) 0
b) 1
c) +1
d) -1
126. The simplest Neural Network is called a ________.
a) Neuron
b) Gene
c) Perceptron
d) Single neuron
127. In rule-based algorithms, _____rules that cover all cases.
a) if-else
b) if-then
c) switch-case
d) nested if
128. The __________is used to predict a future classification value.
a) Genetic algorithm
b) Decision Tree
c) Rule-based Algorithm
d) Neural Network

129. Multiple independent approaches can be applied to a classification problem is referred to as ___.
a) CMC
b) RBF
c) ROC
d) DCS
130. In which technique the classifier that has the best accuracy in database sample?
a) CMC
b) RBF
c) DCS
d) ROC
131. OC stands for_______________.
a) Operating characteristics
b) Operating curve
c) Operating classifications
132. Rule based classification algorithms generate ______ rules to perform the classifications.
a) If
b) Then
c) If-then
d) If - else
133. In OC curve , the horizontal axis has the percentage of _________Positives for a sample DB.
a) False
b) True
c) Either a, b
134. In OC curve , the vertical axis has the percentage of _________Positives for a sample DB.
a) False
b) True
c) Either a, b
135. The__________ approach is most useful in classification problem.

a) Incremental rule
b) Cluster
c) NN
d) Decision tree

136. _________ techniques use labeling of the items to assist In the classification process.
a) Intrinsic
b) Extrinsic
c) Overlapping
d) Numerical
137. A __________ curve shows the relationship between false positives and true positives.
a) BOC
b) ROS
c) ROC
d) BOS
138. Task of CART is_________.
a) Only regression
b) Only classification
c) Both a,b
139. A variation of the complete link algorithm is called ___________ algorithm.
a) Nearest
b) Neighbour
c) Farthest Neighbour
d) All the above
140. K nearest neighbor is a classification scheme based on the use of_________.
a) Distance Measure
b) Similarity
c) Complete link
d) Average
141. A perceptron is a ___________ neuron with multiple inputs and one output.
a) single
b) Multiple
c) Double
142. The classes that exist for a classification problem are indeed _________.
a) Equivalence classes
b) Variance classes
c) Mean classes
d) Median
143. The formula for straight line is_________.
a) Y=mx+b
b) y=mx
c) Y=M+b
d) Y=m

144. _________ are data values that are exception to the usual and expected data.
a) Outliers
b) Noise
c) Error
d) Overfit
145. ________ is an errorneous data.
a) Overfit
b) Outlier
c) Noise
d) Missing
146. ___________ problems deal with the estimation of output value based on input value.
a) Baysian classification
b) K nearest Neighbour
c) Regression
d) All the above
147. ____ problem can be thought of as estimating the formula for a straight line.
a) Regression
b) Linear regression
c) Bayesian classification
d) K nearest neighbour
148. Logistic regression uses ___________ technique.
a) Box plot
b) Logistic curve
c) Straight line
d) Logistic line
149. Decision tree is otherwise called as___________.
a) Classification tree
b) Regression tree
c) K nearest neighbor
d) Clustering tree
150. Data objects are described by a number of ________that capture the basic characteristics of an
object.
a) Data sets
b) Elements
c) Record
d) Attribute

UNIT-IV
151. __________is similar to classification in that data are grouped.
a) Classification
b) Regression
c) Clustering
d) DT
152. One of the first domain in which clustering was used as __________taxonomy.
a) Biological
b) Zoological
c) Mathematical
d) Scientific
153. Cluster results are________.
a) Static
b) Realistic
c) Acoustic
d) Dynamic
154. _______ clustering , the algorithm creates only one set of clusters.
a) Dynamic
b) Hierarchical
c) Partitional
d) Static
155. With ______ clustering, a nested set of clusters to be created.
a) Partitional
b) Hierarchical
c) Dynamic
d) Static
156. In similarity measures, metric attributes satisfy the ______ inequality.
a) Rectangular
b) Triangular
c) Square
d) Circle
157. The ____ is the “middle” of the cluster it need not be actual point in the cluster.
a) Radius
b) Diameter
c) Centroid
d) Metoid

158. The cluster is represented by one centrally located object in the cluster called a______.
a) Centroid
b) Medoid
c) Radius
d) Diameter
159. The ____is the square root of the average mean squared distance from any point in the cluster to
centroid.
a) Radius
b) Medoid
c) Diameter
d) Centroid
160. The _____is the square root of the average mean squared distance between all pairs of points in the
cluster.
a) Radius
b) Medoid
c) Diameter
d) Centroid
161. Largest distance between an element in one cluster and an element in the other is_____.
a) Single Link
b) Complete Link
c) Average Link
d) Centroid
162. Smallest distance between an element in the cluster and an element in the other is____.
a) Centroid
b) Medoid
c) Complete link
d) Single link
163. _________ are sample points with values much different from those of the remaining set of data.
a) Centroid
b) Medoid
c) Outliers
d) Compression
164. In hierarchical clustering , a tree data structure is called ______.
a) Connected component
b) Dendrogram
c) Minimum spanning tree
d) Bond energy

165. The root in the dendrogram tree contains ____ clusters ,where all elements aretogether.
a) Four
b) Three
c) Two
d) One
166. The space complexity for hierarchical algorithms is_______.
a) O(n)
b) O(N+2)
c) O(n2)
d) O(2N)
167. A ________ component is a graph in which there exists a path between any two vertices.
a) Connected
b) Unconnected
c) Nested
d) Stylish
168. A _____ is a maximal graph in which there is an edge between vertices.
a) Connected graph
b) Clique
c) Candidates
d) Dendrogram
169. The ____are sample points with values much different from those of the remaining set of data.
a) Clusters
b) Outliers
c) Candidates
d) Mining
170. _____is the process of identifying outliers in a set of data.
a) Outlier detection
b) Outlier avoidance
c) Outlier collision
d) Outlier prediction
171. The outliers can be detected by well-known tests such as _________-.
a) Chi-square test
b) Random test
c) Discordancy test
d) Unit test

172. Clustering applications include plant and _____ classifications.
a) Medical
b) Biological
c) Zoological
d) Animal
173. ____ clustering , all items are initially placed in one cluster and clusters are repeat.
a) Random
b) Divisive
c) Nearest neighbour
d) Partitional
174. BEA stands for__.
a) Band Echo Algorithm
b) Bond Echo Algorithm
c) Balance Energy Algorithm
d) Bond Energy Algorithm
175. _________is an iterative clustering algorithm.
a) K-means
b) LARGE DB
c) KDD
d) BEA
176. The nearest neighbor algorithm uses ______technique.
a) Single link
b) Complete link
c) Average link
d) Centroid
177. The PAM algorithm also called _______algorithm.
a) K-means
b) K-medoids
c) K-centroid
d) K-radius
178. The time complexity of nearest neighbor algorithm is________.
a) O(n)
b) O(N+2)
c) O(n2)
d) O(2N)

179. In a distributed database, each resulting cluster is called a _______.
a) Horizontal Fragment
b) Vertical Fragment
c) Both(a) & (b)
d) None
180. In neural network, the number of input nodes is the same as the number of___.
a) Levels
b) Clusters
c) Points
d) Attributes
a) Association rule
b) Classification
c) Clustering
d) Genetic Algorithm
cluster into small pieces.
a) Agglomerative
b) Divisive
c) Partition
d) Numeric
183. ________ seeks to find groups of closely related observations so that observations that belong
the same cluster are more similar to each other.
a) Association
b) Anomaly detection
c) Clustering
d) None
a) Clustering
b) Associations
c) Sequential analysis
d) Classification
a) k-medoid
b) k-means
c) STIRR
d) ROCK

186. In ___________ each cluster is represented by one of the objects of the cluster located near the
center.
a) k-medoid
b) k-means
c) STIRR
d) ROCK
a) DBSCAN
b) BIRCH
c) PAM
d) CURE
a) DBSCAN
b) BIRCH
c) PAM
d) CURE
189. _______ is the process of identifying outliers in a set of data.
a) Outlier
b) Outlier detection
c) Segmentation
d) Processing
190. The space complexity of adjacency matrix is_______.
a) O(n)
b) O(kn)
c) O(n2)
d) None o the above
191. A variation of complete link algorithm is called the ______.
a) Farthest nearest neighbor
b) Nearest neighbor
c) Average
d) Single
192. A tree data structure called________ is used to illustrate the hierarchical clustering technique.
a) Dendogramming
b) Dendo
c) Dendogram
d) Dendograms

193. The term _______ indicates the ability of these NN to organize the nodes into clusters based on
the similarity between them.
a) Competitive
b) Non-competitive
c) Self organizing
194. CF stands for_________
a) Clustering Features
b) Clustering future
c) Classification Features
d) Classification Future
195. The space complexity for K-means is_______.
a) O(n)
b) O(kn)
c) n
d) O(n2)
196. The squared error algorithm has _______ type.
a) Hierarchical
b) Partitional
c) Mixed
d) Agglomeative.
197. The time complexity for single link algorithm is__________.
a) O(kn2)
b) O(n)
c) O(kn)
d) O(n2)
198. The squared error clustering algorithm minimizes_______ .
a) Error
b) Squared error
c) Square
d) All the above
199. With _________ clustering the algorithm creates only one set of clusters.
a) Partitional
b) Hierarchical
c) Agglomerative

200. ________ techniques use labeling of the items to assist in the classification process.
a) Intrinsic
b) Extrinsic
c) Both a,b
d) All the above
UNIT-V
201. The purchasing of one product when another product is purchased represents an__________.
a) Decision Tree
b) Association Rule
c) Classification
d) Clustering
202. The ______of an item is the percentage of transactions in which that item occurs.
a) Confidence
b) Support
c) Association rule
d) Itemset
203. The _____is called the number of scans of the database.
a) Support
b) Confidence
c) Strength
d) Both (b) & (c)
204. Potentially large item sets are called ____.
a) Support
b) Confidence
c) Candidates
d) Itemset
205. In association rule algorithm, the notation “P” indicates.
a) Confidence
b) Candidates
c) Partitions
d) Transactions
206. Any subset of a large itemset must be _____.
a) Small
b) Medium
c) Average
d) Large

207. The large itemsets are also said to be _______closure.
a) Upward
b) Middleware
c) Downward
d) None
208. Additional candidates are determined by applying the _________ border function.
a) Positive
b) Negative
c) Average
d) Medium
209. The Apriori algorithm shows the sample is performed using a support called __.
a) High
b) Low
c) Average
d) Smalls
210. The basic _________ reduces the number of database scans to two.
a) Divisive algorithm
b) Parallel algorithm
c) Partition algorithm
d) Sampling algorithm
211. The candidates are partitioned and counted separately at each processor is called____.
a) Data parallelism
b) Task parallelism
c) Candidates
d) Data reduction
212. One data parallelism algorithm is the _____.
a) MSE
b) FIS
c) DDA
d) CDA
213. One task parallelism algorithm is called _____.
a) CDA
b) MSE
c) DDA
d) BCD

214. An algorithm all rules that satisfy a given support and confidence level is called____.
a) Target
b) Type
c) Data type
d) Data source
215. The most common data structure used to store the candidates itemsets and their counts is
a_______.
a) Binary tree
b) B-tree
c) Balanced tree
d) Hash tree
216. Which technique is used to improve on the performance of an algorithm given distribution Or
amount of main memory?
a) Architecture
b) Optimization
c) Parallelism
d) Itemset
217. A leaf node in the hash tree contains_____.
a) Attributes
b) Itemset
c) Candidates
d) Data
218. One incremental approach,______is based on the Apriori algorithm.
a) CDA
b) DDA
c) fast update
d) slow update
219. A variation of generalized rules are _____ association rules.
a) Multiple-level
b) Hierarchical-level
c) Multi-level
d) Hybrid-level
220. A ______ association rule is one that involves categorical and quantitative data.
a) Categorical
b) Qualitative
c) Quantitative
d) Spanning

221. MIS stands for _______.
a) Medium item support
b) Maximum item support
c) Minimum item support
d) Medium item scale
222. A __rule is defined as a set of itemsets that are correlated.
a) Correlation
b) Co-efficient
c) MIS
d) Modification
223. Correlation(A=>B)= ________?
a) P(A,B) / P(A)P(B)
b) (b)P(A) / (P(A) P(B)
c) P(B) / P(A) P(B)
d) P(A) P(B) / P(A) – P(B)
224. Conviction has a value of ____ if A and B are not related.
a) 0
b) 1
c) 2
d) ∞
225. Which one is not an association rule algorithm?
a) Apriori
b) CDA
c) DDA
d) PAM
226. _______ algorithms may be able to adapt better to limited main memory.
a) Divisive
b) Sampling
c) Partitioning
d) Distributed
227. During the _______ scan, additional candidates are generated and counted.
a) First
b) Second
c) Third
d) Fourth

228. Chi-squared statistic is denoted by the _______symbol.
a) X2
b) E[X]
c) 2X
d) X3
229. ___ are used to show the relationships between data items.
a) Clustering
b) Regression
c) Association rules
d) Classification
230. The most two important property of an association rules are _____.
a) Support, confidence
b) Itemset, data
c) Neuron, gene
d) Lift, interest
231. A __________ is defined as a set of itemsets that are correlated.
a) Correlation rule
b) Association rule
c) Conviction
d) Probability of correlation
232. Confidence or strength are indicated by ___________.
a) ©
b) ®
c) €
d) α
233. In association rule l stands for__________.
a) Large item sets in L
b) Set of large item set
c) Both a,b
products.
a) Apriori algorithm
b) Partition algorithm
c) Distributed algorithm
d) Pincer-search algorithm

scans the database.
a) Candidate
b) Primary
c) Secondary
d) Superkey
a) Increases with the size of the maximum frequent set.
b) Decreases with increase in size of the maximum frequent set.
c) Increases with the size of the data.
d) Decreases with the increase in size of the data.
a) Only candidate set
b) No candidate set
c) Only border set
d) No border set
a) Upward
b) Downward
c) Breadthwise
d) Both upward and downward
239. The _______ step eliminates the extensions of (k-1)-itemsets which are not found to be frequent,
from being considered for counting support.
a) Candidate generation
b) Pruning
c) Partitioning
d) Itemset eliminations
b) Itemset generation
c) Pruning
d) Partitioning
b) Itemset generation
c) Pruning
d) Partitioning

a) top-down search
b) breadth first search
c) depth first search
d) bottom-up search
a) width-wise algorithm
b) level-wise algorithm
c) pincer-search algorithm
d) FP growth algorithm
a) Consequent
b) Onset
c) Antecedent
d) Precedent
a) Consequent
b) Onset
c) Antecedent
d) Precedent
246. The value that says that transactions in D that support X also support Y is called ______________.
a) Confidence
b) Support
c) Support count
d) None Of the above
a) Confidence
b) Support
c) Support count
d) None Of the above
a) Sampling
b) Parallelization
c) Both A & B

a) Segmentation
b) Visualization
c) Correction
d) Association
a) Clustering
b) Associations
c) Sequential analysis
d) Classification

ANSWER KEY
UNIT-I
1 A 2 C 3 C 4 A 5 C 6 A 7 B 8 A 9 C 10 A
11 D 12 D 13 A 14 A 15 D 16 B 17 A 18 A 19 C 20 C
21 B 22 B 23 A 24 C 25 B 26 A 27 C 28 A 29 A 30 A
31 D 32 C 33 B 34 D 35 B 36 D 37 D 38 B 39 D 40 B
41 A 42 A 43 D 44 C 45 B 46 A 47 A 48 D 49 A 50 D
UNIT-II
51 A 52 B 53 D 54 A 55 B 56 C 57 A 58 A 59 A 60 A
61 C 62 B 63 C 64 A 65 B 66 C 67 D 68 B 69 B 70 C
71 C 72 B 73 A 74 C 75 C 76 B 77 B 78 C 79 B 80 A
81 A 82 B 83 A 84 C 85 B 86 C 87 B 88 A 89 B 90 A
91 C 92 A 93 A 94 B 95 C 96 C 97 D 98 B 99 B 100 A
UNIT-III

101 B 102 A 103 D 104 A 105 C 106 A 107 D 108 C 109 A 110 C
111 B 112 A 113 B 114 D 115 B 116 C 117 B 118 C 119 D 120 A
121 B 122 A 123 C 124 D 125 A 126 C 127 B 128 D 129 A 130 C
131 A 132 C 133 A 134 C 135 B 136 B 137 C 138 C 139 C 140 A
141 A 142 A 143 A 144 A 145 C 146 C 147 B 148 B 149 A 150 D
UNIT-IV
151 C 152 A 153 D 154 C 155 B 156 B 157 C 158 B 159 A 160 C
161 B 162 D 163 C 164 B 165 D 166 C 167 A 168 B 169 B 170 A
171 C 172 D 173 B 174 D 175 A 176 A 177 B 178 C 179 B 180 D
181 C 182 B 183 C 184 A 185 B 186 A 187 C 188 A 189 B 190 C
191 A 192 C 193 C 194 A 195 A 196 B 197 A 198 B 199 A 200 B
UNIT-V

201 B 202 B 203 D 204 C 205 C 206 D 207 C 208 B 209 D 210 C
211 B 212 D 213 C 214 A 215 D 216 B 217 C 218 C 219 A 220 C
221 C 222 A 223 A 224 B 225 D 226 A 227 B 228 A 229 C 230 A
231 A 232 D 233 A 234 A 235 A 236 A 237 B 238 A 239 B 240 C
241 A 242 B 243 A 244 C 245 A 246 A 247 C 248 C 249 D 250 B

DMW MCQ

Uploaded by

Copyright:

Available Formats

DMW MCQ

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

DMW MCQ

Uploaded by

Copyright:

Available Formats

Seat No -

Total number of questions : 60

12695_Data Mining and Warehousing

2) Attempt any 50 questions out of 60.

3) Use of calculator is allowed.

4) Each question carries 1 Mark.

5) Specially abled students are allowed 20 minutes extra for examination.

6) Do not use pencils to darken answer.

8) No change will be allowed once the answer is marked on OMR Sheet.

9) Rough work shall not be done on OMR sheet or on question paper.

10) Darken ONLY ONE CIRCLE for each answer.

Q.no 1. What does the leaf node in decision tree indicates

Q.no 2. sensitivity is also known as

C : True negatives (TN)

Q.no 4. Removing duplicate records is a process called

Q.no 5. For Apriori algorithm, what is the ﬁrst phase?

Q.no 6. Multi-class classiﬁcation makes the assumption that each sample is

A : one and only one label

C : one or many labels

Q.no 7. Multilevel association rules can be mined eﬃciently using

Q.no 9. Self-training is the simplest form of

A : Social Network Analysis

B : Market Basket Analysis

Q.no 11. Hidden knowledge referred to

A : A set of databases from different vendors, possibly using different database

C : Information that is hidden in a database and that cannot be recovered by a simple

Q.no 13. The Synonym for data mining is

B : Knowledge discovery in database

Q.no 16. Color is an example of which type of attribute

Q.no 17. What are two steps of tree pruning work?

A : Pessimistic pruning and Optimistic pruning

B : Postpruning and Prepruning

D : None of the options

Q.no 18. A data cube is deﬁned by

C : Dimensions and Facts

Q.no 19. For Apriori algorithm, what is the second phase?

Q.no 21. Lazy learner classiﬁcation approach is

C : the network is constructed by human experts

D : None of the options

Q.no 22. Cross validation involves

C : testing the machine with only validation sets

D : testing the machine on only testing datasets.

Q.no 23. The rule is considered as intersting if

A : They satisfy both minimum support and minimum conﬁdence threshold

B : They satisfy both maximum support and maximum conﬁdence threshold

C : They satisfy maximum support and minimum conﬁdence threshold

D : They satisfy minimum support and maximum conﬁdence threshold

Q.no 24. Data independence means

A : Data is deﬁned separately and not included in programs

B : Programs are not dependent on the physical attributes of the data

C : Programs are not dependent on the logiical attributes of the data

Q.no 25. Which of the following is a predictive model?

Q.no 26. The data cubes are generally

Q.no 27. Identify the example of sequence data

C : market basket data

Q.no 28. The frequent-item-header-table consists of number ﬁelds

Q.no 29. How are metarules useful in mining of association rules?

A : Allow users to specify threshold measures