INSTITUTE OF AERONAUTICAL ENGINEERING

(Autonomous)
Dundigal, Hyderabad - 500 043

COMPUTER SCIENCE AND INFORMATION TECHNOLOGY

�
Course Title DATA MINING AND KNOWLEDGE DISCOVERY �
Course Code ACIC01 �
Program [Link] �
Semester VI �
Course Type Core �
Regulation IARE - R20 �
Theory Practical
Course Structure Lecture Tutorials Credits Laboratory Credits
3 - 3 - - �
Course Coordinator [Link] Reddy, Assistant Professor �

COURSE OBJECTIVES:
The students will try to learn:
�
I The scope and essentiality of data warehousing and mining.
�
II The analysis of data, choosing relevant models and algorithms for respective
applications.
�
III The process and mining of complex data types such as streams, spatial, web and
multimedia.
�
IV The research perspectives towards advances in data mining.
�

COURSE OUTCOMES:
After successful completion of the course, students should be able to:
�
CO 1 Relate knowledge discovery in databases (KDD) process with the Understand
help of data warehouse fundamentals and data mining
functionalities �
CO 2 Select appropriate preprocessing techniques on real time data for Apply
usage of data mining algorithms. �
CO 3 Apply Apriori and FP growth methods on transaction data for Apply
frequent pattern mining. �
CO 4 Choose classification or clustering algorithm or building a Apply
classification or prediction model. �
 �
CO 5 Infer complex data models with respect to multimedia, streams, Understand
spatial and web mining. �
CO 6 Examine data mining algorithms for solving real world problems.. Analyze �

QUESTION BANK:
�
MODULE I �
KNOWLEDGE DISCOVERY �
PART A-PROBLEM SOLVING AND CRITICAL THINKING QUESTIONS �
[Link] QUESTION Taxonomy How does this subsume CO’s
the level �
1 Suppose that the data for Apply This would require the CO 6
analysis includes the learner to recall the
attribute age. The age statistical measures and
values for the data tuples explain each. Then compute
are (in increasing order) 13, on the given data.
15, 16, 16, 19, 20, 20, 21, 22,
22, 25, 25,25, 25, 30, 33, 33,
35, 35, 35, 35, 36, 40, 45, 46,
52,70. Compute the
following: (a) Mean of the
data? Median? (b) mode of
the data? Comment on the
data’s modality (i.e.
bimodal, trimodal etc.). (c)
midrange of the data? �

Page 2
 �
2 Suppose that the data for Apply This would require the CO 6
analysis includes the learner to recall the
attribute age. The age preprocessing techniques
values for the data tuples and relate to the given data
are (in increasing order) 13, to perform summarization
15, 16, 16, and visualization then
19,20,20,21,22,22,25,2525, Apply on the given data
25, 30, 33, 33, 35, 35, 35, 35, and visualize in the different
36, 40, 45, 46, 52, 70. plots.
Compute the following: (a)
Can you find (roughly) the
first quartile (Q1) and the
third quartile (Q3) of the
data? (b) Give the
five-number summary of the
data. (c) Show a box plot of
the data. (d) How is a
quantile-quantile plot
different from a quantile
plot? �
3 Suppose that the data for Apply This would require the CO 6
analysis includes the learner to recall the
attribute age. The age preprocessing techniques
values for the data tuples and relate to the given data
are (in increasing order) 13, to perform normalization
15, 16, 16, then apply binning
19,20,20,21,22,22,25,2525, techniques to smoothing
25, 30, 33, 33, 35, 35, 35, 35, and find outliers.
36, 40, 45, 46, 52, 70. (a)
Use smoothing by bin
means to smooth the above
data, using a bin depth of 3.
Illustrate your steps.
Comment on the effect of
this technique for the given
data (b) How might you
determine outliers in the
data? (c) What other
methods are there for data
smoothing? �

Page 3
 �
4 Suppose a group of 12 sales Apply This would require the CO 2
price records as: learner to recall the
5,10,11,13,15,35,50,55,72,92,204,215 preprocessing techniques
Partition them into three and relate to the given data
bins by each of the following to perform normalization
methods: (a) then apply binning
equal-frequency techniques to smoothing
(equal-depth) partitioning and find outliers.
(b) equal-width partitioning
(c) clustering . �
5. Derive data objects and Understand This would require the CO 3
attributes types with learner to recall and relate
suitable examples. data objects and attributes
types with suitable
examples. �
6. Illustrate Knowledge Understand This would require the CO 2
discovery from databases learner to recall KDD
process with suitable process and explain each
examples step with suitable examples. �
7. Explain how data mining as Understand This would require the CO 3
a step in the process of learner to recall KDD
knowledge discovery and process and explain data
how kinds of data can be mining step.
mined? �
8. Explain issues in data Understand This would require the CO 1
mining with real time learner to recall the data
examples? mining major issues with
real time examples. �
9. Explain the differences Understand This would require the CO 2
between the following learner to recall the basics
approaches for the of data base management
integration of a data mining system then compare the
system with a database or given.
data warehouse system. �
10. Explain how to measure the Understand
This would require the CO 1
data similarity and learner to recall the data
dissimilarity in KDD. similarity and dissimilarity
in KDD. �
PART B-LONG ANSWER QUESTIONS �

Page 4
 �
1. What is data mining? In Understand This would require the CO 3
your answer, address the learner to recall the data
following: (a) Is it hype? mining functionalities then
(b) Is it a simple explain about the query
transformation of processing technique.
Technology developed from
Databases, statistics, and
machine learning? �
2. Explain with an example Understand This would require the CO 1
where data mining is crucial learner to recall the data
to the success of a business. mining functionalities then
What data mining functions explain about the query
does this business need? processing technique.
Can they be performed
alternatively by data query
processing or simple
statistical analysis? �
3. Explain the difference Understand This would require the CO 3
between discrimination and learner to recall the basics
classification? Between of data clustering methods
characterization and then differentiate the given.
clustering? Between
classification and
prediction? For each of
these pairs of tasks, how are
they similar? �
4. Explain the challenges Understand This would require the CO 3
incurred in data mining in learner to recall the basics
specific to user interaction? of data mining then explain
the issues in data mining. �
5. Outline data mining Understand This would require the CO 3
functionalities with real life learner to recall and relate
example the data mining
functionalities with real life
examples. �
6. Illustrate Knowledge Understand This would require the CO 2
discovery from databases learner to recall KDD
process with process steps process and explain each
step. �
7. Explain how data mining as Understand This would require the CO 3
a step in the process of learner to recall KDD
knowledge discovery? process and explain data
mining step. �

Page 5
 �
8. Explain issues to consider Understand This would require the CO 1
during data integration? learner to recall the data
mining major issues then
explain the issues during
data integration. �
9. Explain the differences Understand This would require the CO 2
between the following learner to recall the basics
approaches for the of data base management
integration of a data mining system then compare the
system with a database or given.
data warehouse system: no
coupling, loose coupling,
semi tight coupling, and
tight Coupling. State which
approach you think is the
most popular, and why? �
10. Explain Data quality can be Understand This would require the CO 1
assessed in terms of learner to recall the data
accuracy, completeness, and mining major issues then
consistency. Propose two explain the data quality,
other dimensions of data consistency.
quality. �
11. List out the different Understand This would require the CO 1
applications of Data Mining learner to recall applications
with reaitime examples? of Data Mining with
reaitime examples. �
12. Discuss the data objects Understand – CO 2
with suitable examples? �
13. Derive the attribute types Understand This would require the CO 1
with suitable examples? learner to recall attribute
types with suitable
examples. �
14. Define basic statistical Understand This would require the CO 1
descriptions of data with learner to recall the basic
real time examples ? statistical descriptions of
data with real time
examples �
15. Explain steps involved in Understand This would require the CO 3
data mining knowledge learner to recall data mining
process with suitable knowledge process with
examples. suitable examples and
explain how they can
implement. �

Page 6
 �
16. What are some common Understand This would require the CO 3
problems occurs in learner to recall common
measuring the data problems occurs in
similarity and dissimilarity measuring the data
in KDD. similarity and dissimilarity
in KDD. �
17. What are the major Understand This would require the CO 3
elements of data mining and learner to recall the major
explain with suitable elements of data mining.
example? �
18. Name different level of Understand
This would require the CO 2
analysis of data mining? learner to recall and relate
different level of analysis of
data mining. �
19. Name methods of Understand This would require the CO 1
classification methods? learner to recall methods of
classification methods �
20. Explain Statistical Analyze This would require the CO 1
Procedure Based Approach learner to recall the
with suitable examples? Statistical Procedure Based
Approach with suitable
examples. �
PART-C - SHORT ANSWER QUESTIONS �
1. Define data mining. Understand – CO 1 �
2. List the steps involved in Remember – CO 1
knowledge discovery in
databases (or) KDD
method? �
3. Compare data mining and Understand This would require the CO 3
data warehouse. learner to recall the basics
of data mining and data
warehouse concept then
compare both. �
4. List any three functionality Understand – CO 3
of data mining. �
5. List out major issues in Understand – CO 3
data mining �
6. What are the spatial Remember – CO 3
temporal databases? �
7. Define Data quality. Remember – CO 2 �
8. List object –oriented Understand – CO 2
Databases? �
9. What are the spatial Remember – CO 3
temporal databases? �

Page 7
 �
10. Compare heterogeneous Remember This would require the CO 2
databases and legacy learner to recall the basics
databases? of data base management
system then compare the
heterogeneous databases
and legacy databases. �
11. Explain Evolution and Remember This would require the CO 1
deviation analysis? learner to recall Evolution
and deviation analysis. �
12. Why Fuzzy logic is an Remember – CO 2
important area for Data
Mining? �
13. Define Clustering in Data Understand This would require the CO 1
Mining? learner to recall Clustering
in Data Mining. �
14. What is Supervised and Remember This would require the CO 1
Unsupervised Learning in learner to recall the
data mining? Supervised and
Unsupervised Learning in
data mining. �
15. Give an introduction to Remember This would require the CO 3
data mining query language learner to recall data mining
with syntax? query language with
sysntax. �
16. Differentiate Between Data Remember This would require the CO 3
Mining And Data learner to recall and relate
Warehousing with the Data Mining And Data
examples? Warehousing with examples. �
17. What is Data Purging in Remember This would require the CO 3
data mining? learner to recall and relate
Data Purging in data
mining. �
18. Explain how to work with Understand This would require the CO 2
data mining algorithms learner to recall and relate
included in SQL server data data mining algorithms
mining? included in SQL server data
mining. �
19. Explain Over-fitting in data Remember This would require the CO 1
mining? learner to recall Over-fitting
in data mining. �
20. Can you explain the process Understand This would require the CO 1
of Tree Pruning in data learner to recall the process
mining? of Tree Pruning in data
mining. �

Page 8
 �
MODULE II �
DATA PREPROCESSING �
PART A-PROBLEM SOLVING AND CRITICAL THINKING �
[Link] QUESTION Taxonomy How does this subsume CO’s
the level �
1. Suppose your task as a Understand This would require the CO 1
software engineer at Big learner to recall the basics
University is to design a of data mining & data
data mining system to warehouse concept then
examine the university compare the given.
course database, which
contains the following
information: the name,
address, and status (e.g.,
undergraduate or graduate)
of each student, the courses
taken, and the cumulative
grade point average (GPA).
Explain the architecture you
would choose. What is the
purpose of each component
of this architecture? �
2. The exceptions in credit Understand This would require the CO 6
card transactions can help learner to recall the data
us detect the fraudulent use warehouse architecture then
of credit cards. Taking explain the each component
fraudulence detection as an of this architecture.
example, List two methods
that can be used to detect
outliers and discuss which
one is more reliable. �

Page 9
 �
3. Consider the following data Apply – CO 2
for analysis includes the
attribute age. The age
values for the data tuples
are (in increasing order) 13,
15, 16, 16, 19, 20, 20, 21, 22,
22, 25, 25, 25, 25, 30, 33, 33,
35, 35, 35, 35, 36, 40, 45, 46,
52, 70. a) Use min-max
normalization to transform
the value 35 for age on to
the range [0.0, 1.0]. b) Use
z-score normalization to
transform the value 35 for
age, where the standard
deviation of age is 12.94
years. c) Use normalization
by decimal scaling to
transform the value 35 for
age. d) Comment on which
method you would prefer to
use for the given data,
giving reasons as to why. �
4. Outline the evolutions of Understand This would require the CO 2
database technology lead to learner to recall the
data mining? preprocessing techniques,
relate the different
normalization techniques to
the given problem. Apply
on the given data and
perform analysis and
identify the appropriate
technique for the given
problem. �
5. Give an introduction to Understand – CO 1
data mining query language
in data mining system. �
6. What is Syntax for Understand – CO 3
Task-Relevant Data
Specification in DMQL. �
7. What is Syntax for Understand – CO 3
Specifying the Kind of
Knowledge? �

Page 10
 �
8. Explain Syntax for Understand This would require the CO 2
Interestingness Measures learner to recall the
Specification? Interestingness Measures
Specification in DMQL. �
9. Explain Syntax for Pattern Understand – CO 3
Presentation and
Visualization Specification? �
10. Explain Data Mining Understand – CO 3
Languages Standardization? �
PART B-LONG ANSWER QUESTIONS �
1. Explain briefly about the Understand This would require the CO 3
data smoothing techniques? learner to recall the data
cleaning method then
explain data smoothing
technique. �
2. Explain Data Integration Understand This would require the CO 2
and Transformation? learner to recall the data
cleaning method then
explain data integration and
transformation. �
3. Classify the various data Understand This would require the CO 2
reduction techniques? learner to recall the data
cleaning method then
explain the data reduction
techniques. �
4. Express the different Understand This would require the CO 3
techniques for handling learner to recall the data
Missing values in data cleaning method then
cleaning process? explain the data reduction
techniques. �
5. Explain Redundancy and Understand This would require the CO 2
Correlation Analysis for learner to recall
finding duplicate attributes preprocessing techniques
and tubles. and explain correlation
analysis. �
6. Summarize data reduction Understand This would require the CO 3
strategies used in learner to recall
preprocessing. preprocessing techniques
and explain data reduction
stratagies. �

Page 11
 �
7. The data are a list of Apply This would require the CO 2
AllElectronics prices for learner to recall and relate
commonly sold items reduction techniques in data
(rounded to the nearest preprocessing and then
dollar). The numbers have apply histogram method on
been sorted: 1, 1, 5, 5, 5, 5, sales data.
5, 8, 8, 10, 10, 10, 10, 12,
14, 14, 14, 15, 15, 15, 15, 15,
15, 18, 18, 18, 18, 18, 18, 18,
18, 20, 20, 20, 20, 20, 20, 20,
21, 21, 21, 21, 25, 25, 25, 25,
25, 28, 28, 30, 30, 30. Use a
histogram singleton buckets
for identifying ranges in
reduction process. �
8. Explain the following Understand This would require the CO 5
advanced database systems learner to recall the
and applications: object- multimedia database
relational databases, spatial concepts then explain the
databases, text databases, given.
multimedia databases,
stream data, the World
Wide Web. �
9. Illustrate concept hierarchy Understand This would require the CO 1
for the attribute price, learner to recall and relate
where an interval (X...Y] concept hierarchy in
denotes the range from discretization process.
X(exclusive)toY
(inclusive). In discretization
of price. �
10. Solve the two methods Apply This would require the CO 2
below to normalize the learner to recall the data
following group of data: mining preprocessing
200, 300, 400, 600, 1000 techniques and use min-max
min-max normalization by and z-score for normalizing
setting min = 0 and max = the given data
1 z-score normalization �
11. What are the different tasks Understand This would require the CO 1
of Data Mining? learner to recall different
tasks of Data Mining in
data preprocessing. �
12. Discuss the Life cycle of Understand – CO 2
Data Mining projects? �

Page 12
 �
13. What is Data Cube Understand This would require the CO 1
Aggregation in data learner to recall Data Cube
preprocessing? Aggregation involved in
data preprocessing. �
14. Define Attribute Subset Understand This would require the CO 1
Selection? learner to recall the
Attribute Subset Selection
in data preprocessing. �
15. Why we need Numerosity Understand This would require the CO 3
Reduction? learner to recall Numerosity
Reduction techniques and
explain how they can
implement. �
16. What are some common Understand This would require the CO 3
problems that occur during learner to recall
Dimensionality Reduction? Dimensionality Reduction in
preprocessing techniques. �
17. Explain Binning Methods in Understand This would require the CO 3
data cleaning? learner to recall and relate
the Binning Methods in
data cleaning �
18. Discuss Regression Methods Understand This would require the CO 2
in data cleaning? learner to recall and relate
Regression Methods in data
cleaning. �
19. Derive Clustering Methods Understand This would require the CO 1
in data cleaning? learner to recall Clustering
Methods in data cleaning. �
20. Can you explain the process Understand This would require the CO 1
of Data Transformation in learner to recall the Data
data preprocessing? Transformation in data
preprocessing. �
PART C-SHORT ANSWER QUESTIONS �
1. Compare classification and Remember This would require the CO 3
Prediction? learner to recall the data
mining classification
methods then compare
classification and prediction
techniques. �
2. Give classification of data Remember – CO 2
mining system. �
3. List the types of data that Understand – CO 3
can be mined? �

Page 13
 �
4. What is data object in data Remember – CO 2
base. �
5. List the different techniques Understand – CO 1
used in data transformation. �
6. List data mining task Understand – CO 3
primitives. �
7. Give the steps in data Remember – CO 3
preprocessing �
8. Explain the outlier analysis? Understand This would require the CO 2
learner to recall the
clustering methods then
explain about the outlier
analysis. �
9. Name the steps involved in Remember – CO 3
data preprocessing? �
10. What is dimensionality Remember – CO 3
reduction and its
importance in data mining? �
11. Define Data reduction? Remember This would require the CO 1
learner to recall Data
reduction involved in data
preprocessing. �
12. What is meant by Data Remember – CO 2
discretization? �
13. What is the discretization Remember This would require the CO 1
processes involved in data learner to recall
preprocessing? discretization processes
involved in data
preprocessing. �
14. Define Concept hierarchy? Remember This would require the CO 1
learner to recall the concept
hierarchy in data
preprocessing. �
15. Why we need data Remember This would require the CO 3
preprocessing? learner to recall
preprocessing techniques
and explain how they can
implement. �
16. What are some common Remember This would require the CO 3
problems that occur during learner to recall
data processing? How can preprocessing techniques
they be fixed? and explain how they are
fixed. �

Page 14
 �
17. What’s the difference Remember This would require the CO 3
between missing value learner to recall and relate
treatment and outliers the missing value treatment
treatment? and outlier treatment. �
18. Can you give me an example Remember This would require the CO 2
of how smoothing might be learner to recall and relate
used for noise reduction? smoothing techniques in
noise reduction. �
19. How can we use correlation Understand This would require the CO 1
analysis to remove learner to recall the
redundant variables from coorelation analysis in data
our dataset? preprocessing. �
20. Can you explain the Remember This would require the CO 1
purpose of principal learner to recall the
component analysis (PCA)? principle component
analysis in data
preprocessing. �
MODULE III �
DATA WAREHOUSING AND ONLINE ANALYTICAL PROCESSING �
PART A-PROBLEM SOLVING AND CRITICAL THINKING QUESTIONS �
[Link] QUESTION Taxonomy How does this subsume CO’s
the level �
1 Illustrate a Hierarchical and Understand This would require the CO 1
lattice structures of learner to recall and relate
attributes in warehouse the concepts of concept
dimensions for location and hierarchy structures and
time. illustrate for dimensions
location and time. �

Page 15
 �
2 Suppose that a data Apply This would require the CO 1
warehouse contains 20 learner to recall and relate
dimensions, each with about the concepts of concept
five levels of granularity. hierarchy with illustration
Users are mainly interested representation.
in four particular
dimensions, each having
three frequently accessed
levels for rolling up and
drilling down. (a) Illustrate
a data cube structure to
efficiently support this
preference? (b) At times, a
user may want to drill
through the cube, down to
the raw data for one or two
particular dimensions.
Select a OLAP operation to
support this feature? �
3 Suppose that a data Understand This would require the CO 1
warehouse for Big learner to recall and relate
University consists of the the concepts of
following four dimensions: multi-dimensional modelling
student, course, semester, and represent with suitable
and instructor, and two illustration.
Measures count and average
grade. When at the lowest
conceptual level (e.g., for a
given student, course,
semester, and instructor
combination), the average
grade measure stores the
actual course grade of the
student. At higher
combination. (a) Illustrate
snowflake schema for
modelling university data
warehouse �

Page 16
 �
4 Suppose that a data Apply This would require the CO 1
warehouse consists of the learner to recall and relate
four dimensions, date, the concepts of
spectator, location, and multi-dimensional modelling
game, and the two
measures, count and charge,
where charge is the fare
that a spectator pays when
watching a game on a given
date. Spectators may be
students, adults, or seniors,
with each category having
its own charge rate. Show
an appropriate schema for
the data warehouse. �
5 Radio-frequency Understand This would require the CO 1
identification is commonly learner to recall and relate
used to trace object the concepts of
movement and perform multi-dimensional modelling
inventory control. An RFID for the given dimensions.
reader can successfully read
an RFID tag from a limited
distance at any scheduled
time. Suppose a company
wants to design a data
warehouse to facilitate the
analysis of objects with
RFID tags in an online
analytical processing
manner. The company
registers huge amounts of
RFID data in the format of
(RFID, at location, time),
and also has some
information about the
objects carrying the RFID
tag, for example, (RFID,
product name, product
category, producer, date
produced, price). Show a
data warehouse model to
facilitate effective
registration and online
analytical processing of such
data. �

Page 17
 �
6 Radio-frequency Understand This would require the CO 1
identification is commonly learner to recall and relate
used to trace object the concepts of analytical
movement and perform processing then Choose an
inventory control. An RFID appropriate structure for
reader can successfully read the given dimensions to
an RFID tag from a limited perform analytical
distance at any scheduled processing.
time. Suppose a company
wants to design a data
warehouse to facilitate the
analysis of objects with
RFID tags in an online
analytical processing
manner. The company
registers huge amounts of
RFID data in the format of
(RFID, at location, time),
and also has some
information about the
objects carrying the RFID
tag, for example, (RFID,
product name, product
category, producer, date
produced, price). You may
want to perform online
analytical processing to
determine how many TV
sets were shipped from the
LA seaport to BestBuy in
Champaign, IL, by month,
brand, and price range.
Outline how this could be
done efficiently if you were
to store such RFID data in
the warehouse. �
7 Compare Snowflake schema, Understand This would require the CO 1
fact constellation, starnet learner to recall
query model multi-dimensional modelling
and then compare each one
with other. �

Page 18
 �
8 In data warehouse Understand This would require the CO 1
technology, a multiple learner to recall the
dimensional view can be implementation techniques
implemented by a relational of data warehouse about
database technique then explain each technique.
(ROLAP), or by a
multidimensional database
technique (MOLAP), or by
a hybrid database technique
(HOLAP). (a) For each
technique, explain how each
of the following functions
may be implemented: i.
The generation of a data
warehouse (including
aggregation) ii. Roll-up iii.
Drill-down Which
implementation techniques
do you prefer, and why? �
9 Model a warehouse the Understand This would require the CO 1
appropriate schema, which learner to recall the
specifies two fact tables, multi-dimensional data
sales and shipping. The model then construct a
Sales table have four model with appropriate
dimensions: time, item, schema for sales warehouse.
branch, and location. The
shipping table has five
dimensions, or keys—item
key, time key, shipper key,
from location, and to
location—and two
measures—dollars cost and
units shipped. �

Page 19
 �
10 Suppose that a data Understand This would require the CO 1
warehouse for big-university learner to recall and relate
consist of the following four the OLAP operations on
dimensions: Student, multi-dimensional data cube
Course, Semester and at possible levels.
Instructor, and two
measures count and avg
grade. When at the lowest
conceptual level (Ex. For a
given student, course,
semester and instructor
combination), the avggrade
measure stores the actual
course grade of the student.
At higher conceptual levels,
avg grade stores the average
grade for the given
combination. Starting with
the base cuboid [Student,
Course, Semester,
Instructor], what specific
OLAP operations (eg
Roll-up from Semester to
Year) should one perform in
order to list the average
grade of CS courses for each
big-university students. �
PART B-LONG ANSWER QUESTIONS �
1. Compare operational Understand The learner to recall the CO 1
database systems and data operational database
warehousing? concepts and compare with
data warehouse systems. �
2. “Data warehouse is a Understand This would require the CO 1
subject oriented, integrated, learner to recall the basic
time variant and nonvolatile concepts of data warehouse
collection of data” Explain? then explain about the
characteristics of data in
data warehouse. �
3. Explain the reasons for a Understand This would require the CO 1
separate data warehouse of learner to recall the basic
organization? concepts of data warehouse
then explain the reasons of
separation of data
warehouse. �

Page 20
 �
4. Explain slice and pivot Understand This would require the CO 1
operations on data cube learner to recall the
with a neat sketch? structure of multi
dimensional view then
illustrate slice and pivot
operations on data cube. �
5. Outline the processing of Understand This would require the CO 1
OLAP operations with a learner to recall the
suitable example? structure of multi
dimensional view then
explain the processing of
OLAP operations. �
6. How a data warehouse is Understand - CO 1
different from a database?
How are they similar? �
7. Summarize different Understand This would require the CO 1
measures used in data learner to recall the multi
warehouse construction with dimensional data models
an example? then explain about the
concept of measures. �
8. Describe various types of Understand This would require the CO 2
OLAP Servers with learner to recall the
functionalities? structure of multi
dimensional view then
explain the types of OLAP
Servers. �
9. Explain the data warehouse Understand This would require the CO 1
Back-End Tools? learner to recall the data
warehouse architecture then
explain about the data
warehouse Back-End Tools. �
10. Explain the three-tier Understand This would require the CO 2
architecture of a data learner to recall the
warehouse with a neat structure of data warehouse
sketch. then explain the
components included in
three-tier architecture. �
11. Explain about Metadata Understand This would require the CO 1
Repository with learner to recall the data
functionalities? warehouse implementation
then explain about the
Metadata Repository. �

Page 21
 �
12. What is data integration Understand – CO 2
and its need in data
warehouse? �
13. Explain about the data Understand This would require the CO 1
warehouse implementation learner to recall the basics
with an example? of data warehouse concept
then explain the data
warehouse implementation. �
14. Compare OLAP and OLTP Understand This would require the CO 1
in view of operational and learner to recall the
transactional databases analytical and transactional
data processing then
compare each in various
functions. �
15. Translate a relational Understand This would require the CO 1
database into a data learner to recall and relate
warehouse cube with a the relational database
suitable example structure to warehouse
structure. �
16. Compare Enterprise Understand This would require the CO 1
warehouse, data mart, and learner to recall the data
virtual warehouse? warehouse model then relate
the data mart and virtual
warehouse. �
17. Illustrate a concept Understand This would require the CO 3
hierarchy of attributes time learner to recall and relate
and location. the concept hierarchy on
given attributes. �
18. Outline OLAP operations Understand This would require the CO 2
on data cube(location, learner to recall and relate
items, time). OLAP operations on given
data cube. �
19. Summarize the Understand This would require the CO 1
functionalities of various learner to recall the 3 tier
components in data data warehouse architecture
warehouse layer then explain the warehouse
layer components in detail. �
20. Explain ETL (extract, Understand This would require the CO 1
transform, load) of data learner to recall the 3 tier
warehousing in detail. data warehouse architecture
then explain the ETL Tools
of data warehouse. �

Page 22
 �
PART-C - SHORT ANSWER QUESTIONS �
1. Define online analytical Remember – CO 1
processing. �
2. List the key features of data Understand – CO 1
warehouse. �
3. Define data mart. Remember – CO 1 �
4. Define enterprise warehouse. Remember – CO 1 �
5. Define repository. Remember – CO 1 �
6. Define metadata. Remember – CO 1 �
7. List various Understand – CO 1
multidimensional data
models. �
8. Explain about the star Understand This would require the CO 2
schema? learner to recall the multi
dimensional data models
then explain about the star
schema. �
9. Explain the snowflake Understand This would require the CO 3
schema? learner to recall the multi
dimensional data models
then explain about the
snowflake schema. �
10. Explain about the fact Understand This would require The CO 2
constellation model? learner to recall the multi
dimensional data models
then explain about the
constellation model. �
11. Name the OLAP operations. Remember – CO 1 �
12. What is slice and dice Remember – CO 2
operation? �
13. Define Pivot operation? Remember – CO 3 �
14. Define concept hierarchy Remember – CO 2
with an example. �
15. Explain the various views of Understand This would require the CO 1
data warehouse design? learner to recall the basics
of data warehouse concept
then explain the various
design concepts. �
16. Define Relational OLAP Remember – CO 3
(ROLAP) server? �

Page 23
 �
17. Explain Multidimensional Understand This would require the CO 3
OLAP (MOLAP) server? learner to recall the multi
dimensional data model
then explain about the
MOLAP. �
18. What is Hybrid OLAP Understand – CO 2
(HOLAP) server? �
19. Define Data warehouse? Remember – CO 3 �
20. Show concept hierarchy of Remember – CO 3
time? �
MODULE IV �
MINING FREQUENT PATTERNS AND CLASSIFICATION �
PART A-PROBLEM SOLVING AND CRITICAL THINKING �
[Link] QUESTION Taxonomy How does this subsume CO’s
the level �
1. Discuss about frequent item Understand This would require the CO 3
set? Write the Apriori learner to recall the Pruning
algorithm for frequent item Pattern Space with Pattern
set generation? Explain Pruning Constraints then
with an example. explain the Apriori
algorithm for frequent item
set generation with an
example. �
2. Discuss about Market Understand This would require the CO 3
basket analysis with learner to recall the
suitable example. applications of frequent
pattern mining methods
then explain about the
market basket analysis with
example. �
3. Give examples for frequent Understand This would require the CO 3
item sets and explain the learner to recall the frequent
join step and pruning step. item set generation then
explain about the join and
pruning steps. �
4. Illustrate why is tree Understand This would require the CO 3
pruning useful in decision learner to recall the basic
tree induction? Explain the classification methods then
drawback of using a explain tree pruning in
separate set of tuples to decision tree induction.
evaluate pruning? �

Page 24
 �
5. Given a decision tree, you Understand This would require the CO 3
have the option of (a) learner to recall the basic
converting the decision tree concepts of decision tree
to rules and then pruning then explain the conversion
the resulting rules, or (b) of decision tree to rules.
pruning the decision tree
and then converting the
pruned tree to rules.
Explain advantage does (a)
have over (b)? �
6. Outline the major ideas of Understand This would require the CO 3
naive Bayesian learner to recall the Bayes
classification. Explain why Classification methods and
is naïve Bayesian then explain thre given.
classification called “naive”? �
7. Develop an efficient method Analyze This would require the CO 3
that performs effective naive learner to recall the Bayes
Bayesian classification over Classification methods and
an infinite data stream (i.e., then develop the algorithm
you can scan the data for that.
stream only once). If we
wanted to discover the
evolution of such
classification schemes (e.g.,
comparing the classification
scheme at this moment with
earlier schemes, such as one
from a week ago),Construct
modified design would you
suggest? �
8. Explain K- Nearest neighbor Understand This would require the CO 3
classification-Algorithm and learner to recall the
Characteristics with k-Nearest-Neighbor
example. Classifiers methods then
explain with an algorithm. �
9. Explain in detail How does Understand This would require the CO 3
the Naïve Bayesian learner to recall the Bayes
classification works? Classification methods then
explain how it works. �

Page 25
 �
10. What is associative Understand – CO 2
classification? Why is
associative classification
able to achieve higher
classification accuracy than
a classical decision tree
method? Explain how
associative classification can
be used for text document
classification. �
11. It is difficult to assess Understand – CO 2
classification accuracy when
individual data objects may
belong to more than one
class at a time. In such
cases, Explain on what
criteria you would use to
compare different classifiers
modeled after the same
data. �
12. Specify the 5 criteria for the Understand – CO 3
evaluation of classification
& prediction? �
13. (a) Explain the algorithm Understand
This would require the CO 2
for constructing a decision learner to recall the basic
tree from training samples. classification methods then
(b) Explain Bayes theorem. explain the decision tree
induction and Bayes therem. �
PART B- LONG ANSWER QUESTIONS �
1. Define the terms frequent Understand – CO 3
item sets, closed item sets
and association rules? �
2. Discuss which algorithm is Understand This would require the CO 3
an influential algorithm for learner to recall the frequent
mining frequent Item sets item set mining methods
for boolean association then explain about the
rules? Explain with an Boolean association rules.
example? �
3. Describe the different Understand – CO 3
techniques to improve the
efficiency of Apriori?
Explain? �

Page 26
 �
4. Discuss the FP-growth Understand This would require the CO 3
algorithm? Explain with an learner to recall the frequent
example? item set methods and
pattern growth approach
then explain about the
FP-growth algorithm. �
5. Explain how to mine the Understand This would require the CO 3
frequent item sets using learner to recall the frequent
vertical data format? item set generation then
explain how to mine
frequent item set using
vertical data format. �
6. Discuss about mining Understand This would require the CO 3
multilevel association rules learner to recall the pattern
from transaction databases mining in multilevel then
in detail? explain about the multilevel
association rules from
transaction databases. �
7. Explain how to mine the Understand This would require the CO 2
multidimensional learner to recall the pattern
association rules from mining in multilevel then
relational databases and explain about the multi
data warehouses? dimensional association
rules from relational
databases. �
8. Describe briefly about the Understand This would require the CO 2
different correlation learner to recall the
measures in association constraint-based pattern
analysis? generation then explain
different correlation
measures in association
analysis. �
9. Discuss about Understand This would require the CO 3
constraint-based association learner to recall the
mining? constraint-based association
mining then discuss about
that. �
10. Explain the Apriori Understand This would require the CO 2
algorithm with example? learner to recall the Pruning
Pattern Space with Pattern
Pruning Constraints then
explain the Apriori
algorithm. �

Page 27
 �
11. Explain the generating Understand This would require the CO 3
association rules from learner to recall the
frequent item sets. association rule mining
concept then explain about
the generation of association
rules from frequent item
sets. �
12. Discuss about mining Understand This would require the CO 2
multilevel association rules learner to recall the mining
from transaction databases association rules then
in detail? explain about the
transaction databases. �
13. Describe multidimensional Understand – CO 3
association rules using static
Discretization? �
14. Explain what are additional Understand This would require the CO 2
rule constraints to guide learner to recall the mining
mining? association rules then
explain about the additional
rule constraints to guide
mining. �
15. Explain, how can we tell Understand This would require the CO 1
which strong association learner to recall the mining
rules are really interesting? association rules then
Explain with an example? explain about the given
with an example. �
16. Describe about the Understand – CO 3
correlation analysis using
Chi-square? �
17. Describe about the Mining Understand – CO 3
closed Frequent Item set �
18. Write a short example to Understand – CO 2
show that items in a strong
association rule may
actually be negatively
correlated. �

Page 28
 �
19. Explain Association rule Understand This would require the CO 3
mining often generates a learner to recall the mining
large number of rules. association rules then
Discuss effective methods explain about the
that can be used to reduce preventing rules of
the number of rules association rule mining.
generated while still
preserving most of the
interesting rules. �
20. Name the pruning strategies Understand This would require the CO 3
in mining closed frequent learner to recall the mining
item sets? association rules then
explain about the pruning
strategies. �
21. Explain about the Understand This would require the CO 4
classification and prediction learner to recall the concept
with an Example? of Outlier Detection then
explain classification and
prediction method with an
example. �
22. Explain about basic decision Understand This would require the CO 3
tree induction algorithm? learner to recall the basic
concepts of classification
then explain decision tree
induction algorithm. �
23. How various measures Understand – CO 3
associated with attribute
selection? �
24. How does tree pruning Understand – CO 3
work? What are some
enhancements to basic
decision tree induction? �
25. Explain how scalable is Understand This would require the CO 3
decision tree induction? learner to recall the basic
Explain? concepts of classification
then explain decision tree
induction algorithm. �
26. Explain the working Understand This would require the CO 3
procedures of simple learner to recall the Bayes
Bayesian classifier? Classification methods
explain working procedures
of simple Bayesian classifier. �

Page 29
 �
27. Explain Bayesian Belief Understand This would require the CO 2
Networks? learner to recall the Bayes
Classification methods
explain the Bayesian Belief
Networks. �
28. Explain about k-nearest Understand This would require the CO 2
neighbor classifier and learner to recall the
case-based reasoning? k-Nearest-Neighbor
Classifiers methods then
explain case based
reasoning. �
29. Explain about classifier Understand This would require the CO 3
accuracy? Explain the learner to recall the basic
process of measuring the concepts of classifier
accuracy of a classifier? accuracy then explain
process of measuring the
accuracy of classifier. �
30. How the ideas can be Understand This would require the CO 2
applied to any association learner to recall the basic
rule mining? Explain. concepts of Association
classification then explain
how it can be applied. �
31. Explain about the major Understand This would require the CO 3
issues regarding learner to recall the
classifications and classifications and
predictions? predictions techniques then
explain the issues regarding
classifications and
predictions. �
32. Compare classification and Understand This would require the CO 2
prediction methods? learner to recall the
classifications and
predictions techniques then
compare them. �
33. Explain briefly various Understand This would require the CO 3
measures associated with learner to recall the basic
attribute selection? concepts of data mining
then explain about the
attribute selection. �
34. Explain training of Bayesian Understand This would require the CO 2
belief networks? learner to recall the Bayes
Classification methods
explain the Bayesian Belief
Networks. �

Page 30
 �
35. How tree pruning useful in Understand – CO 1
decision tree induction?
What is a drawback of using
a separate set of tuples to
evaluate pruning? �
36. Explain for a given a Understand This would require the CO 3
decision tree, you have the learner to recall the basic
option of (a) converting the concepts of decision tree
decision tree to rules and then explain the conversion
then pruning the resulting of decision tree to rules.
rules, or (b) pruning the
Decision tree and then
converting the pruned tree
to rules. What advantage
does (a) have over (b)? �
37. Compare the advantages Understand This would require the CO 3
and disadvantages of eager learner to recall the Bayes
classification (e.g., decision Classification methods and
tree, Bayesian, neural decision tree concepts then
network) versus lazy list the advantages and
classification (e.g., k- disadvantages of the given.
nearest neighbor, case-
based reasoning). �
38. Write an algorithm for Understand This would require the CO 2
k-nearest-neighbor learner to recall the
classification given k and n, k-Nearest-Neighbor
the number of attributes Classifiers methods then
describing each tuple. explain with an algorithm. �
39. Develop each of the Apply This would require the CO 3
following clustering learner to recall the
algorithms in terms of the clustering methods then
following criteria: (i) shapes develop the k-means and
of clusters that can be k-medoids algorithm for
determined; (ii) input given.
parameters that must be
specified; and (iii)
limitations. (a)k-means
(b)k-medoids �
40. Classification is supervised Understand
This would require the CO 3
learning, Justify. and learner to recall the basic
Explain different classification methods then
classification Techniques. explain different types of
classification technique. �
PART C- SHORT ANSWER QUESTIONS �

Page 31
 �
1. Define association rule? Remember – CO 3 �
2. Define item set? Remember – CO 3 �
3. Define frequent item sets? Remember – CO 3 �
4. List the measures of Understand – CO 3
association rules? �
5. List the types of association Understand – CO 3
rules? �
6. What is the principle of Remember – CO 3
APRIORI algorithm? �
7. Specify the problem Understand – CO 2
definition for association
rules? �
8. What is support and Remember – CO 2
minimum support? �
9. What is confidence and Remember – CO 3
minimum confidence for
strong association rule? �
10. Name the steps in Remember – CO 2
association rule mining? �
11. Explain the two kinds of Understand This would require the CO 3
closure checking? learner to recall the frequent
item set generation then
explain about the kinds of
closure checking. �
12. Explain the five categories Understand This would require the CO 3
of pattern mining learner to recall the
constraints? advanced pattern mining
methods then explain the
categories of pattern mining
constraints. �
13. List the techniques of Understand – CO 3
efficiency of Apriori
algorithm? �
14. List the drawbacks of Understand – CO 3
Apriori technique? �
15. How can we mine closed Understand This would require the CO 3
frequent item sets? Explain. learner to recall the
advanced pattern mining
methods then explain about
the mining of frequent item
set. �
16. Name the pruning strategies Remember – CO 3
of closed frequent item sets? �

Page 32
 �
17. Name the rule of support Remember – CO 2
for item sets? �
18. Compare the two kinds of Understand This would require the CO 2
closure checking? learner to recall the frequent
item set methods then
Compare the kinds of
closure checking. �
19. List the techniques to Understand – CO 3
improve the efficiency of
Apriori algorithm? �
20. Write the procedure to find Remember – CO 2
association rule from given
frequent item sets? �
21. Define classification? Remember – CO 4 �
22. Define regression analysis? Remember – CO 4 �
23. Name the steps in data Remember – CO 4
classification? �
24. Define training tuple? Remember – CO 4 �
25. Explain accuracy of a Understand This would require the CO 3
classifier? learner to recall the General
Approach to Classification
methods then explain the
accuracy of a classifier. �
26. Compare supervised Understand This would require the CO 3
learning and unsupervised learner to recall the General
learning? Approach to Classification
methods then compare
supervised learning and
unsupervised learning. �
27. Define the decision tree? Remember – CO 4 �
28. Define information gain? Remember – CO 4 �
29. State gain ratio? Understand – CO 4 �
30. State Gini index? Understand – CO 4 �
31. Define tree pruning? Remember – CO 3 �
32. Define the construction of Remember – CO 2
naïve Bayesian
classification? �

Page 33
 �
33. Explain the IF-THEN rules Understand This would require the CO 3
for classification? learner to recall the Tree
Pruning concept then
explain how a rule-based
classifier can be constructed
by extracting IF-THEN
rules. �
34. Explain Decision Tree Understand This would require the CO 2
Induction? learner to recall scalability
methods then explain
Decision Tree Induction. �
35. List the Attribute Selection Understand – CO 1
Measures? �
36. Define Bayes’ Theorem? Remember – CO 4 �
37. Define Naïve Bayesian Remember – CO 3
Classification? �
38. Define K-Nearest-Neighbor Remember – CO 2
Classifiers? �
39. Explain the essential Understand This would require the CO 3
features of decision trees in learner to recall the
context of classification. classification methods then
explain the given. �
40. What are the advantages Remember – CO 4
and disadvantages of
decision tress over other
classification methods? �
MODULE V �
CLUSTERING AND RESEARCH FRONTIERS �
PART A-PROBLEM SOLVING AND CRITICAL THINKING �
[Link] QUESTION Taxonomy How does this subsume CO’s
the level �
1. Given the following Understand – CO 3
measurements for the
variable age: 48, 12, 25, 42,
28,43,33,35, 56, 28,
standardize the variable by
the following: Compute (a)
The mean absolute
deviation of age. (b)The
z-score for the first four
measurements. �

Page 34
 �
2. Given two objects Understand – CO 3
represented by the tuples
(22, 1, 42, 10) and (20, 0,
36,8): Compute (a) The
Euclidean distance between
the two objects. (b)The
Manhattan distance
between the two objects. (c)
The Minkowski distance
between the two objects,
using p = 3. �
3. Suppose that the data Understand – CO 3
mining task is to cluster the
following eight points (with
(x, y) representing location)
into three clusters. A1(2,
10), A2(2, 5), A3(8 , 4),
B1(5, 8),B2(7, 5), B3(6, 4),
C1(1, 2), C2(4, 9). The
distance function is
Euclidean distance. Suppose
initially we assign A1, B1,
and C1 as the center of each
cluster, respectively. Use
the k-means algorithm to
show only The three cluster
centers after the first round
of execution and The final
three clusters �
4. Explain why is it that Understand This would require the CO 3
BIRCH encounters learner to recall the
difficulties in finding clusters clustering methods then
of arbitrary shape but explain about the types of
OPTICS does not? Can you hierarchical methods.
propose some Modifications
to BIRCH to help it find
clusters of arbitrary shape? �

Page 35
 �
5. Explain each of the Understand This would require the CO 3
following clustering learner to recall the
algorithms in terms of the clustering methods then
following criteria: (i) shapes explain the given.
of clusters that can be
determined; (ii) input
parameters that must be
specified; and (iii)
limitations. k-means (b)
k-medoids (c) CLARA �
6. Develop the PAM Understand This would require the CO 3
Algorithm with example learner to recall the
and Write the key issue in clustering methods then
hierarchical clustering develop the
algorithm. PAM(Partitioning Around
Medoids) algorithm with
examples. �
7. List out the different Understand – CO 2
clustering methods?
Explain in detail. �
8. Given the following Understand – CO 3
measurements for the
variable age: 29, 31, 25, 41,
27,43,33,35 56, 28,
standardize the variable by
the following: Compute The
mean absolute deviation of
age. The z-score for the first
three measurements. �
9. Given two objects Understand – CO 2
represented by the tuples
(21, 2, 41, 11) and (21, 1,
32,6): Compute (a) The
Euclidean distance between
the two objects. (b)The
Manhattan distance
between the two objects. (c)
The Minkowski distance
between the two objects,
using p = 2. �
10. Explain the working of Understand – CO 2
dendogram in the
agglomerative hierarchical
clustering algorithm. �

Page 36
 �
PART B- LONG ANSWER QUESTIONS �
1. Explain the various types of Understand This would require the CO 3
data in cluster analysis? learner to recall the
clustering methods then
explain about the types of
data in cluster analysis. �
2. Explain the categories of Understand This would require the CO 3
major clustering methods? learner to recall the
clustering methods then
explain about the categories
of clustering method. �
3. Identify the algorithms for Understand This would require the CO 3
k-means and k-medoids? learner to recall the
Explain? clustering methods then
develop the k-means and
k-medoids algorithms. �
4. Explain the different types Understand This would require the CO 3
of hierarchical methods? learner to recall the
clustering methods then
explain about the types of
hierarchical methods. �
5. Demonstrate about the Understand This would require the CO 3
following hierarchical learner to recall the
methods a) BIRCH b) clustering methods then
Chameleon explain about the types of
hierarchical methods. �
6. Explain about Understand This would require the CO 3
semi-supervised cluster learner to recall the
analysis? clustering methods then
explain about the
semi-supervised cluster
analysis. �
7. Explain about the outlier Understand This would require the CO 2
analysis? learner to recall the outlier
detection methods then
explain about the outlier
analysis. �
8. Define the distance-based Understand – CO 2
outlier? Illustrate the
efficient algorithms for
mining distance-based
algorithm? �

Page 37
 �
9. Explain about the Understand This would require the CO 3
Statistical-based outlier learner to recall the outlier
detection? detection methods then
explain about the
Statistical-based outlier
detection methods. �
10. Explain about the Understand This would require the CO 2
distance-based outlier learner to recall the outlier
detection? detection methods then
explain about the
distance-based outlier
detection method. �
11. Explain about the Understand This would require the CO 3
density-based outlier learner to recall the outlier
detection? detection methods then
explain about the
density-based outlier
detection method. �
12. Demonstrate about the Understand This would require the CO 2
deviation-based outlier learner to recall the outlier
detection techniques? detection methods then
explain about the
deviation-based outlier
detection techniques. �
13. Demonstrate about the Understand This would require the CO 3
BIRCH hierarchical learner to recall the
methods? clustering methods then
explain about the types of
hierarchical methods. �
14. standardize the variable by Understand – CO 2
the following: (a) Compute
the mean absolute deviation
of age. (b) Compute the
z-score for the first four
measurements. �
15. Illustrate the strength and Understand This would require the CO 1
weakness of k-means in learner to recall the
comparison with the k- clustering methods then
medoids algorithm. Also, compare k-means and
illustrate the strength and k-medoids algorithms with
weakness of these schemes strengths and weakness.
in comparison with a
hierarchical clustering
scheme (such as AGNES). �

Page 38
 �
16. Explain why is outlier Understand This would require the CO 3
mining important? Briefly learner to recall the outlier
describe the different detection methods then
approaches behind explain about the different
statistical-based outlier approaches behind these
detection, distanced-based outlier detection method.
outlier detection,
density-based local outlier
detection, and
deviation-based outlier
detection. �
17. Explain briefly mining of UnderstandThis would require the CO 3
multimedia databases and learner to recall the concept
time series databases. of multimedia database then
explain the mining of
multimedia data. �
18. Explain the process of Understand This would require the CO 2
mining the World Wide learner to recall the concept
Web. of multimedia database then
explain the mining process
of World Wide Web. �
19. Explain the various types of Understand This would require the CO 3
web mining. learner to recall the concept
of multimedia database then
explain the Web mining. �
20. Explain about model based Understand This would require the CO 3
clustering methods. learner to recall the
clustering methods then
explain about the model
based clustering methods �
PART C- SHORT ANSWER QUESTIONS �
1. Define Clustering? Remember – CO 3 �
2. Illustrate the meaning of Understand This would require the CO 3
cluster analysis? learner to recall the
clustering methods then
explain about the cluster
analysis. �
3. Explain the fields in which Understand This would require the CO 3
clustering techniques are learner to recall the
used? clustering methods then
explain about the clustering
techniques. �
4. List out the requirements of Understand – CO 3
cluster analysis? �

Page 39
 �
5. List the different types of Understand – CO 3
data used for cluster
analysis? �
6. State interval scaled Understand – CO 3
variables? �
7. Define Binary variables? Remember – CO 2
And what are the two types
of binary variables? �
8. Define nominal, ordinal and Remember – CO 2
ratio scaled variables? �
9. Illustrate mean by Understand This would require the CO 3
partitioning method? learner to recall the
clustering methods then
explain about the
partitioning method. �
10. Define CLARA and Remember – CO 2
CLARANS? �
11. State hierarchical method? Understand – CO 3 �
12. Compare agglomerative and Understand This would require the CO 2
divisive hierarchical learner to recall the
clustering? clustering methods then
compare the given. �
13. State K-Means method? Understand – CO 3 �
14. Define Outlier Detection? Remember – CO 2 �
15. Define Chameleon method? Remember – CO 1 �
16. Explain different data types Understand This would require the CO 3
used in clustering. learner to recall the
clustering methods then
explain different types. �
17. What is a multimedia Remember – CO 3
database? �
18. Define graph mining. Remember – CO 2 �
19. Define sequence mining. Remember – CO 3 �
20. Define web mining. Remember – CO 3 �

Course Coordinator: HOD CSE

Page 40