Department of Computer Science and Engineering

&
Department of Information Technology

QUESTION BANK

For ALL 5 UNITS

DESCRIPTIVE & OBJETIVE QNS

COURSE: B. Tech (CSE-A,B,C) III Year – I Semester (R18)

For Both CSE(A,B,C) & IT

SUBJECT: DATA ANALYTICS

1
 UNIT-1
COURSE PROGRAM BLOOM’S
S.No QUESTION MARKS OUTCOME OUTCOME TAXONOMY
(CO) (PO) LEVEL(BTL)
Why Data Analytics is so 2M 1 1 1
a).
important?
What do you mean by Enterprise 3M 1 1 1
1. b).
requirements in Data architecture?
Describe the Factors that influence 10M 1 2 2
c).
the Data Architecture?

What are the tools used in Data 2M 1 1 1

a).
Analytics?
What are the three essential models 3M 1 1 2
2. b).
in data architecture?
What are primary sources of data? 10M 1 2 4
c).
Explain in detail

a). What are CRD & RBD? 2M 1 1 1

Differentiate Qualitative Data & 3M 1 2 3
b).
3. Quantitative Data.
List and explain about the 10M 1 4 2
c).
secondary sources of data

Write about sensor’s data & Web 2M 1 2 4

a).
traffic data.
Brief about the features of Amazon 3M 1 1 4
4. b).
Web Services - S3
Explain about the detection and 10M 1 2 3
c).
treatment of Outliers

What do you mean by Data 2M 1 1 1

a).
Quality?
What is the difference between 3M 1 3 1
5. b).
error data and noisy data?
Explain about the Data Pre- 5M 1 2 2
c).
processing in detail

What is the objective of Data 2M 1 1 1

a).
Processing?
How do you handle the missing 3M 1 2 2
6. b).
values?
Explain about the Data Processing 10M 1 4 3
c).
in detail.

2
 UNIT 2
BLOO
PROG
COURSE M’S
RAM
OUTCO TAXON
S.No QUESTION MARKS OUTC
ME OMY
OME
(CO) LEVEL(
(PO)
BTL)
a). What is the Importance of Analytics? 2M 2 1 1
1. b). What is the role of Data Analytics? 3M 2 1 2
c). What are the ways to use the Data Analytics? 10M 2 2 4

List three tools of DA those works on stack of

a). 2M 2 1 1
Hadoop.
2. b). Brief any Four tools used in Data Analytics? 3M 2 2 2
What are the steps involved in Data Analytics?
c). 10M 2 1 4
Explain in detail.

a). Write short notes on Data Modelling. 2M 2 1 1

b). Brief some applications of DA. 3M 2 1 2
3.
What are the different primary Analytics Tools for
c). 10M 2 2 2
DA? Explain in detail

a). List the Features of Apache Spark? 2M 2 1 1

b). Why and where Scala & Impala are useful? 3M 2 1 2
4.
Illustrate about Apache Spark Built and components
c). 10M 2 2 2
in Hadoop.

a). What are the features of Impala? 2M 2 1 1

b). What is Cluster Computing? Brief about it. 3M 2 1 2
5.
Contrast the differences about SQL & NOSQL
c). 10M 2 2 2
databases.

a). What are the benefits of NOSQL? 2M 2 1 1

6. b). Write short notes on different data types and variables 3M 2 2 2
c). Explain in detail about the Missing Imputations 10M 2 3 4

3
 UNIT 3
BLOOM’S
COURSE PROGRAM
TAXONOMY
S.No QUESTION MARKS OUTCOME OUTCOME
LEVEL(BTL
(CO) (PO)
)
a). When a Regression is chosen? 2M 3 1 1
b). List the Regression Analysis Techniques 3M 3 1 2
1. Explain in detail about the OLS 10M 3 3 4
c). Regression with the inclusion of Error
term?

What are the advantages and Limitation 2M 3 1 1

a).
of Linear Regression
How do you Calculate the B1 & B0 using 3M 3 1 2
b).
2. Correlation and Standard Deviation?
Write and Explain the Properties and 10M 3 1 4
c). Assumption of OLS Regression along
with Root Mean Squared Error.

What do you mean by Unbiasedness and 2M 3 1 2

a).
Least Variance?
3. b). Elaborate Variable Rationalization? 3M 3 2 1
Illustrate the Model Building Life Cycle 10M 3 4 4
c).
in Data Analytics.

a). What is a sufficient Estimator? 2M 3 1 1

Compare Homoscedasticity & 3M 3 1 2
b).
4. Heteroscedasticity.
Compare and contrast SQL Databases 10M 3 2 3
c).
with NOSQL Databases.

a). What is Univariate Analysis? 2M 3 1 1

Explain Discrete and continuous Variables 3M 3 1 2
b).
5. with example.
Sketch various analytics applications to 10M 3 1 4
c).
various Business Domains.

What is the need of Business Modelling 2M 3 1 2

a).
and Model Theory?
What are different types of NOSQL 3M 3 2 1
6. b).
Databases
What are Missing Imputations? Explain in 10M 3 3 4
c).
detail

4
 UNIT 4
COURSE PROGRAM BLOOM’S
S. No QUESTION MARKS OUTCOME OUTCOME TAXONOMY
(CO) (PO) LEVEL(BTL)
a). What is Supervised Learning? 2M 4 2 1
What is the major difference between 3M 4 1 2
b).
1. Supervised & Unsupervised Learning?
Compare and contrast Supervised & 10M 4 3 4
c).
Unsupervised Learning.

a). What is Unsupervised Learning? 2M 4 1 1

List some Supervised and Unsupervised 3M 4 1 2
b).
2. Learning Techniques.
Explain in detail about the Segmentation 10M 4 1 4
c).
approach in Data Analytics

Explain in brief about the types of 2M 4 1 2

a).
Decision Tree Algorithms.
Write the terminologies in Decision Tree 3M 4 2 1
b).
3. and representation
Explain in detail about the Decision Tree 10M 4 4 4
c). along with algorithm and simple
example

Compare and Contrast Entropy & 2M 4 1 1

a).
Information Gain?
What are the appropriate Problems for 3M 4 1 2
4. b).
Decision Tree Learning? Explain
Write the advantages, Limitations of 10M 4 2 3
c).
DTL.

a). What is Pruning in DTL? 2M 4 2 2

b). Compare Overfitting and Under fitting. 3M 4 1 4
5.
Discuss about Time Series Methods in 10M 4 3 1
c).
Data Analytics.

a). Brief about ARMA and ARIMA 2M 4 2 3

Compare Classification vs Regression 3M 4 3 2
b).
6. and their Methods and CART.
Interpret ETL Approach in Data 10M 4 1 4
c).
Analytics

5
 UNIT 5
COURSE PROGRAM BLOOM’S
S. No QUESTION MARKS OUTCOME OUTCOME TAXONOMY
(CO) (PO) LEVEL(BTL)
What do you mean by Data Visualization? 2M 5 2 1
a).
Brief.
Why Data Visualization is required? 3M 5 1 2
b).
1. Elaborate
Explore in detail about the different 10M 5 3 5
c). Geometric Projection Visualization
Techniques.

a). What is a Tree Map? 2M 5 1 1

What are the different Categories of Data 3M 5 1 2
b).
2. Visualizations?
Explain steps involved in Data 10M 5 1 5
c).
Visualization In Tableau.

a). What is a Line plot? 2M 5 1 2

b). How the Pie Chart represented? 3M 5 2 1
3.
Explain in detail about the Icon-Based 10M 5 5 5
c).
Visualization Techniques

a). What is a scatter plot? 2M 5 1 1

b). What is a Box Plot? 3M 5 1 2
4.
Explain about the Hierarchical 10M 5 2 3
c).
Visualization Techniques.

a). What is Circle packing? 2M 5 2 2

Write and brief the different 3M 5 1 5
b).
terminologies used in Box Plot.
5.
What is a Word Cloud? Explore the 10M 5 3 1
c). Visualizing the Complex Data and
Relations.

What is a Chernoff Face and Sticky 2M 5 2 3

a).
Figure?
6. b). List few tools popular for ETL approach 3M 4 3 2
What are Time Series Methods? Explore 10M 4 1 5
c).
ARIMA & ARMA.

6
 OBJECTIVE QUESTIONS
UNIT – 1
Choose the Correct Answer
1. Most of the data is generated from _________ [ ]
A. Print media B. Organizations
C. Social media D. e-commerce

2. Data Analytics is used to gather ___________in Data. [ ]

A. hidden insights B. perform market analysis
C. Interesting Patterns D. All the above

3. Market Analysis can be performed to understand the _________of competitors. [ ]

A. strengths B. weaknesses
C. Both Strengths and weaknesses D. Profits and loss

4. __________ policies and rules will help describe the manner in which enterprise wishes [ ]
to process their data.
A. Working Policies B. Labor Policies
C. Business policies D. Administration

5. The General Approach is based on designing the Architecture at __________ Levels [ ]

of Specification.
A. Logical Level B. Physical
C. Implementational Level D. All

6. _______________ is a group of non-numerical data such as words, sentences. [ ]

A. quantitative data B. Big Data
C. qualitative data D. Analytics

7. The data which is Raw, original, and extracted directly from the official sources is [ ]
known as _____________.
A. Secondary Data B. primary data
C. Input Data D. Processed Data

8. CRD _______________ [ ]
A. Complete Randomized design B. Complete Rough Data
C. Complete Raw Data D. Complete Raw Design

9. LSD – Latin Square Design is _________ squares with an equal number of rows and [ ]
columns
A. N x N B. N x M
C. N x 1 D. 1 x N

10. __________ is the assessment of how much the data is usable and fits its serving [ ]
context.
A. data quality B. Data Integrity

7
 C. Data Quantity D. Data Interpretability

FILL IN THE BLANKS:

11. ANOVA __________________.

12. __________is the data which has already been collected and reused again for some valid
purpose.
13. ___________ is about handling of missing data, noisy data etc.
14. ____________ is a term referred to storing and accessing data over the internet.
15. Amazon S3 ___________________.
16. __________ is a point or an observation that deviates significantly from the other observations.
17. Reasons for outliers ____________________.
18. Increase in the error variance and reduces the power of statistical tests due to ____________.
19. PMM: _____________.
20. ________________ approach groups the similar data

UNIT-2
Choose the Correct Answer:
1. ______ is leading analytics tool used for statistics and data modeling. [ ]
A. Java Programming B. C Programming
C. R Programming D. C++ Programming

2. ___________ software that connects to any data source such as Excel, corporate [ ]
Data Warehouse, etc.
A. Tableau B. R
C. Java D. Python

3. _________ can be assembled on any platform like SQL server, a MongoDB database [ ]
or JSON.
A. Java Programming B. Python Programming
C. R Programming D. C++ Programming

4. _______________ provides various machine learning and visualization libraries such [ ]

as Scikit-learn, TensorFlow, Matplotlib, Pandas, Keras, etc.
A. Java Programming B. Python Programming
C. R Programming D. C++ Programming

5. _______ is one of the largest large-scale data processing engine that executes [ ]
applications in Hadoop clusters.
A. Python B. R
C. Ruby D. Apache Spark

6. ___________Also known as Google Refine. [ ]

A. Open_Refine B. Closed Refine
C. Wide_Refine D. Big Refine

7. ___________ is a collection of tightly or loosely connected computers that work [ ]

8
 together so that they act as a single entity.
A. Cluster computing B. Wide Computing
C. Big Computing D. Close Computing

8. _____________is a lightning-fast cluster computing technology, designed for fast [ ]

computation.
A. Big Computing B. Distributed computing
C. Apache Spark D. MySQL

9. Spark helps to run an application in __________ [ ]

A. Hadoop cluster B. Oracle
C. Big Cluster D. NoSQL

10. ______is a component on top of Spark Core that introduces a new data abstraction [ ]
A. SQL B. Spark SQL
C. Spark D. NoSQL

Choose the Correct Answer

FILL IN THE BLANKS:
21. __________ is a distributed machine learning framework above Spark
22. ___________ is a distributed graph-processing framework on top of Spark
23. Scala is a statically typed programming language that incorporates both ____________
24. Scala primarily runs on ___________.
25. The name Scala is a portmanteau of ______________.
26. Cloudera Impala is Cloudera's open source massively parallel processing ___________.
27. Cloudera Impala is a query engine that runs on _______________ .
28. ___________ Database is a non-relational Data Management System.
29. MongoDB is an example for _________ Database for Document oriented data.
30. Example of Graph Database __________ .

9
 UNIT-3
MULTIPLE CHOICE QUESTIONS:
1. The term __________ is used to indicate the estimation or prediction of the average [ ]
value of one variable for a specified value of another variable.

A. Segregation B. Progression
C. Regression D. Aggregation

2. simple linear regression we want to model our data as ________________ [ ]

A. y = B0*x * B1 B. y = B0 + B1 * x
C. y = B1 * x D. y = B0 + x

3. RMSE can be computed as: ________ [ ]

n n

  pi  xi   y  x 
2 2
i i
Err  i 1
Err  i 1

A. n B. n
n n

 p  y   y  x 
2 2
i i i i
Err  i 1
Err  i 1

C. n D. n 1

4. When we have a single input attribute (x) and we want to use linear regression, this is [ ]
called ________________
A. Multiple Linear Regression B. Continuous Linear Regression
C. simple linear regression D. Auto Linear Regression

5. In R, Function used to find the a linear relation between x & y [ ]

A. lm(y,x) B. lm(y~x)
C. Linear(y,x) D. predict(x,y)

6. The goal of is to improve the Data Processing in an optimal way through attribute [ ]
subset selection
A. Rationalization B. Variable correlation
C. Variable Rationalization D. Various Rationalization

7. _____________is a mathematical approach to create a statistical model to forecast [ ]

future behavior based on input test data
A. Progressive modeling B. Professional modelling
C. Predictive modeling D. Pro-active modeling

8. Logistic Regression is ______________ modeling [ ]

A. Supervised B. Semi Supervised
C. Unsupervised D. Reinforcement learning

9. In multinomial Logistic regression, there can be 3 or more possible _________types [ ]

of the dependent variable

10
 A. ordered B. Semi-ordered
C. unordered D. Under ordered

10. In Logistic Regression, the dependent variable must be ___________ in nature [ ]

A. Categorical B. Continuous
C. Correlated D. Classical

FILL IN THE BLANKS:

31. In ordinal Logistic regression, there can be 3 or more possible ______________types of

dependent variables.
32. In _______________, there can be only two possible types of the dependent variables Class-0 &
Class-1.
33. ____________is a statistical phenomenon in which multiple independent variables show high
correlation between each other and they are too inter-related.
34. Logistic Regression uses a complex function, known as the _______________
35. Sigmoid function is _________________
36. False positive is Type-2 Error (True/False) _______________
37. False Negative is Type ________ ( I or II) Error.
38. In _________ error, the actual value was negative but the model predicted a positive value
39. Formula for Precision: ______________
40. Formula for F1-Score: ______________

UNIT-4
MULTIPLE CHOICE QUESTIONS:
1. Supervised learning is a learning method in which models are trained using _______ [ ]
A. Unlabeled data B. Raw Data
C. Labeled data D. Complete Data

2. Unsupervised learning is a method in which _________ inferred from the unlabeled [ ]

input data.
A. Classes B. Patterns
C. Errors. D. outputs

3. Supervised learning needs supervision to _________ the model [ ]

A. update B. Test
C. train D. Both Train & Test

4. The purpose of ___________ is to better understand your customers rather than data [ ]
A. segmentation B. Regression
C. Segregation D. Correlation

5. Demographic Segmentation is a __________ segmentation [ ]

A. Can be Non-Objective or objective B. Non-Objective
C. Objective D. Semi-Objective

11
 6. Decision Tree is a _________________technique [ ]
A. supervised learning B. unsupervised learning
C. Semi-supervised learning D. Non-supervised learning

7. It is a tree-structured classifier, where ___________ represent the features of a dataset [ ]

A. internal nodes & leaf nodes B. Root & Internal nodes
C. Root nodes & leaf nodes D. Leaf nodes

8. If the regression decision tree, the decision or the outcome variable is [ ]

______________
A. Continuous B. Categorical
C. Discrete D. distant

9. _________________is the process of removing the unwanted branches from the tree [ ]
A. Edging B. Pruning
C. Regression D. predicting

10. The decision Tree is _______________to errors [ ]

A. Tolerable B. Non-tolerable
C. Sensitive D. Doesn’t allow

FILL IN THE BLANKS:

11. Supervised learning can be categorized in __________________ problems.

12. _________________ can be classified in Clustering and Associations problems.
13. Linear Regression, Logistic Regression are unsupervised learning models (True/False)
______.
14. Decision Tree is the successor of _____________ .
15. CART is ___________________.
16. The best attribute in the dataset using _________________.
17. _________________is a measure of the randomness in the information being processed.
18. _____________ is a statistical property that measures how well a given attribute separates the
training examples.
19. ______________is a modeling error in statistics that occurs when a function is too closely
aligned to a limited set of data points in turn, will fail in testing.
20. ARIMA is an acronym that stands for ____________________________

12
 UNIT- 5
MULTIPLE CHOICE QUESTIONS:
1. _____________ is the art and practice of gathering, analyzing, and graphically [ ]
representing empirical information.
A. Data Modification B. Data visualization
C. Data Validation D. Data Updating

2. __________ is used to get graphical output from data predictive analytics results. [ ]

A. Tabular Data B. Total Blue

C. Tableau D. Tally

3. Data Visualization induce the viewer to think about the substance rather than [ ]
about________ through graphic design
A. output B. outcome
C. methodology D. error

4. We need to choose the dimensions and measures in the process of __________ Data. [ ]
A. Extracting B. Estimating
C. Expressing D. Exploring

5. _____________are the category type data points such as landing page, source [ ]
medium, etc.
A. Directions B. Dimensions
C. Detections D. Du-points

6. One of the great __________ qualities Tableau has is its ability to filter data in real [ ]
time
A. show room B. Show space
C. Show case D. Work space

7. DPA: ____________________ [ ]
A. Data presentation architecture B. Dual presentation architecture
C. Data preparation architecture D. Directive presentation architecture

8. Data visualization is viewed by many disciplines as a modern equivalent of [ ]

___________
A. Virtual Communication B. Viral Communication
C. Visual Communication. D. Vivid Communication

9. ____________ is both an art and a science. [ ]

A. Data Virtualization B. Data Visualization
C. Data Variation D. Data Variance

10. __________can be more precise and revealing than conventional statistical [ ]

computations.
A. Data Representation B. Data Virtualization
C. Graphical representation D. Graphical Computation

13
FILL IN THE BLANKS:

11. Gain insight into an information space by mapping data onto ______________ provide
qualitative overview of large data sets.
12. ________________ is a Forecast Accuracy can be defined as the deviation of Forecast or
Prediction from the actual results.
13. In MFA, Error = _______________.
14. CHAID stands for ___________________.
15. Regression tree analysis is when the predicted outcome can be considered a
________________.
16. A ___________ tree is a binary decision tree that is constructed by splitting a node into two
child nodes repeatedly
17. Decision Tree Leaning can be able to handle both numerical and categorical data (True/False)
______________.
18. Decision Tree uses a White box Model (True/False) _______________.
19. Regression trees / parallel regression modeling, in which the dependent variable
is______________ .
20. The CART growing method attempts to _____________ within-node homogeneity.

14