A.Y.

2024-25 Data Mining IV Year I Sem

Department of Computer Science and Engineering
UNIT-1
S.NO QUESTION MARKS CO PO BTL
1.a What is Data Warehouse? Define data mining 2 1 1 1
1.b Discuss the types of the data can be Mined. 3 1 1 2
1.c Describe the various phases in knowledge 5 1 1 1
discovery process with a neat diagram.
1.d Explain about Data Mining Functionalities. 5 1 1 2
2.a Discuss about Interestingness Patterns 2 1 1 2
2.b List out the applications of data mining. 3 1 3 1
2.c Explain about Classification of Data mining 5 1 1 2
Systems.
2.d Describe about data mining task primitives 5 1 2 1
3.a Discuss about subset selection 2 2 1 2
3.b Discuss about the Issues to be considered 3 1 2 2
during Data Integration
3.c Explain how to integrate data mining system 5 1 2 2
with a data warehouse.
3.d Discuss the major issues in data mining. 5 1 2 2
4.a Define predictive mining 2 1 1 1
4.b Discuss the challenges associated with data 3 1 2 2
mining
4.c Explain the need or significance of data 10 1 2 2
preprocessing and various forms of
preprocessing.
Or
Explain the significance of data preprocessing
in data mining.
5.a Define outlier analysis? 2 1 1 1
5.b List the methods of filling missing values. 3 1 2 1
5.c Differentiate between data mining and data 5 1 1 2
warehouse.
5.d Explain about the Data Cleaning techniques in 5 1 2 2
detail.
6.a Define Stepwise forward selection 2 1 1 1
6.b State binning can handle noisy data? 3 1 2 1
6.c Describe Data Normalization methods in brief 5 1 1 1
6.d Explain briefly about Dimensionality Reduction. 5 1 1 2
7.a How do task primitive contribute to the overall 2 1 1 1
effectiveness of data mining? Explain
7.b List the Numerosity Reduction methods 3 1 1 1
7.c Explain Briefly about Data Cube aggregation, 5 1 2 2
attribute subset selection, Data Discretization
and Concept hierarchy generation.
7.d “Data preprocessing is necessary before data 5 1 2 2
mining process”. Justify your answer.
 Unit-2

S.NO DESCRIPTION OF QUESTION MARKS CO PO BTL

1.a Define frequent itemset? 2 2 1 1
1.b Show how to compute confidence of an association 3 3 2 2
rule? Give example
1.c Explain the process of finding frequent patterns 10 3 2 2
2.a Define maximal frequent item set. 2 2 1 1
2.b Describe about association rule mining? 3 3 3 1
2.c Give an overview of correlation analysis. 5 3 1 2
2.d Explain the measures of association rule mining? 5 3 3 2
Explain
3.a Describe maximal frequent itemset? 2 2 1 1
3.b Differentiate frequent subsequence and frequent 3 2 1 2
substructure.
3.c Compute all the frequent item sets using Apriori 10 3 3 3
algorithm for the given data where min-sup = 2.

4.a Define Support of an association rule. 2 3 1 1

4.b Define Association rule mining two step process 3 3 1 1
4.c Apply FP-Growth algorithm to the following data for 5 3 3 3
finding frequent item sets, consider support threshold
as 30%.
TID List of ItemIDs
1 I1, I2, I4, I5
2 I2, I4, I7
3 I2,I3,I4,I5
4 I1,I3,I4,I7
5 I1,I2,I3,I4,I5
6 I3,I4,I5,I6

4.d Explain in detail about multilevel association rules. 5 3 1 2

5.a Explain the purpose of Apriori algorithm. 2 3 3 2
5.b Give a note on Closed Frequent Item 3 3 1 2
5.c Describe various types of association rules. 5 3 1 1
5.d Write a short notes on constraint based association 5 3 1 2
mining.
6.a Quote an example for quantitative association rule. 2 3 3 1
6.b Write the FP-graph algorithm 3 3 1 1
6.c Explain about the identification of sub graphs in a 5 3 3 2
graph
6.d Write a short note on SPM algorithm? 5 3 1 2
7.a What is the advantage of rule based classification 2 3 3 1
system.
7.b Describe the role of correlation analysis in identifying 3 3 1 1
relationships within dataset.
7.c How constraint based method does influences the 5 3 3 2
discovery of association rule

7.d Explore different mining methods used in various 5 3 1 2

association rule mining and discuss advantages and
limitations

Unit-3

S.NO DESCRIPTION OF QUESTION MARKS CO PO BTL

1.a Define classification? 2 3 1 1
1.b Compare the methods of classification and 3 3 3 2
prediction
1.c Explain classification as a two step process 5 3 1 2
1.d Explain the way of evaluating performance of 5 3 3 2
classification model? Explain.
2.a Why are decision trees useful? 2 4 1 1
2.b List the advantages of using decision trees. 3 4 2 1
2.c Discuss about Decision tree induction 10 3 2 2
algorithm with an example
3.a Define the significance of information gain? 2 3 1 1
3.b Explain the need for tree pruning in decision 3 3 2 2
tree induction?
3.c Describe Bayesian Belief Network with an 10 3 1 1
example.
4.a Define Pre pruning and post pruning. 2 3 1 1
4.b Explain the merits and de-merits of the lazy 3 4 2 2
learning method.
4.c Discuss in detail about rule-based 5 3 2 2
classification.
4.d Briefly explain classification problems and 5 3 2 2
general approaches to solve them.
5.a Define associative classification? 2 3 1 1
5.b Discuss about attribute selection measure 3 3 2 2
Information Gain.
5.c Explain the way of solving a classification 5 3 3 2
problem using k-nearest neighbor algorithm?
5.d Describe about Lazy Learners classification. 5 3 2 1
Explain the merits and de-merits of the lazy
learning method.
6.a Define test data? 2 3 1 1
6.b List the characteristics of k-nearest neighbor 3 3 1 1
algorithm
6.c How does basian classifier handle uncertinity. 5 3 2 2

6.d Discuss decision tree over fitting and pruning 5 3 2 2

techniques

Unit-4

S.NO DESCRIPTION OF QUESTION MARKS CO PO BTL

1.a Define Clustering? 2 3 1 1

1.b Explain the applications of cluster analysis. 3 4 3 2
1.c Explain different Clustering Methods? 10 3 1 2
2.a Define outlier? 2 4 1 1
2.b Describe K-Means Additional issues? 3 4 3 1
2.c Illustrate K-mean algorithm with an example. 10 3 3 2
3.a Discuss the two approaches to improve quality of 2 4 3 2
hierarchical clustering.
3.b List out all partitioning methods for clustering data. 3 5 1 1
3.c Give a brief note on PAM(K-Medoids) Algorithm with 10 5 3 2
example
4.a Discuss the two approaches to improve quality of 2 4 2 2
hierarchical clustering
4.b Explain Hierarchical clustering. 3 5 1 2
4.c Discuss hierarchical methods for clustering and 6 5 1 2
contrast agglomerative and divisive approaches.
4.d Discuss the merits and demerits of hierarchical 4 4 2 2
approaches for clustering
5.a Define categorical variable? 2 4 1 1
5.b Compare agglomerative and divisive methods. 3 4 1 2
5.c How density based method is used for clustering? 5 5 2 2

5.d Discuss about the drawbacks of k-means 5 5 2 2

algorithm? How can we modify the algorithm to
diminish that problem?
Or
Illustrate K-mean algorithm with an example.
6.a Define interval-scaled variables? 2 5 1 1
6.b Differentiate between clustering and classification 3 5 1 2
6.c Explain the following. 5 5 1 2
a) Cluster analysis.
b) Grid–based methods.
6.d Compare and contrast rule based classification 5 5 1 2
systems with decision tree induction.

UNIT -5
S.NO DESCRIPTION OF QUESTION MARKS CO PO BTL

1.a Define data stream mining? 2 5 1 1

1.b Explain the applications of Web Mining? 3 5 3 2
1.c Explain in detail about Time series Mining. 10 5 1 2
2.a Define Structured data? 2 6 1 1
2.b Describe the Terminology of Web Structure? 3 5 1 1
2.c Explain the following: 10 5 3 2
i) Spatial data mining.
ii) Mining sequence patterns in transactional
databases
3.a Define Text Mining? 2 5 1 1
3.b Explain the methods under Text Transformation. 3 6 1 2
3.c Explain the way of applying the mining techniques to 10 5 3 2
unstructured text database? Explain with example
4.a Give examples for unstructured text. 2 5 3 2
4.b Give the taxonomy of web mining. 3 6 2 2
4.c Discuss various kinds of patterns to be mined from 5 5 2 2
web/server logs in web usage mining.
4.d Discuss in detail about web content mining 5 5 2 2
5.a Define stop words? 2 5 1 1
5.b Explain the Advantages & Disadvantages of Text 3 6 2 2
Mining?
5.c Explain about the Multimedia data mining 10 5 2 2
6.a Define NLP? 2 5 1 1
6.b List the applications of web usage mining. 3 6 3 1
6.c Explain about the World wide web mining 10 5 1 2