Department of Artificial Intelligence & Data Sciences

Question Bank
Each question carries 15 Marks

Program: M.Tech(AI&DS) Course: DATA MINING

Course Code:
UNIT-I

Knowledge
S.N Marks CO
Question Level
O
1 a) What is data mining? Explain the steps in 7M 1 L1
data mining process.
b)Explain about Knowledge presentation in 8M 1 L4
mining.
2 a) What is the need to build a data warehouse? 7M 1 L2
Write and explain various steps to buildthe data
warehouse
b) Discuss the type of knowledge discovery in 8M 1 L2
data mining. Explain diagrammatically.
3 a) What is descriptive and predictive data 7M 1 L1
mining?
b) With an example data warehouse explain 8M 1 L4
various schemas used to represent multi
dimensional data.
4 a) Explain the types of OLAP server in detail. 7M 1 L1
.Relational OLAP (ROLAP) • Multidimensional
OLAP (MOLAP)
• Hybrid OLAP (HOLAP) • Specialized SQL
Servers
b) “Data preprocessing techniques can improve 8M 1 L2
the quality of data”-Justify this statement.
5 a) Difference between supervised learning and 7M 1 L1
unsupervised learning.
b)How to integrate data mining system with 8M 1 L4
data base and data warehouse system? Explain.
6 a)Explain about Summary Statistics 7M 1 L1
b) Explain about multi- dimensional data analysis. 8M 1 L1

7 a)Explain about Data Quality 7M 1 L1

b) Explain about Data Processing. 8M 1 L1
 UNIT-II

Knowledge
Marks CO
S.NO Question Level
1 a) What are the steps involved in preparing the data 7M 2 L1
for classification?
b) Explain the algorithm for constructing a decision 8M 2 L4
tree from training samples.
2 a) What do mean by attribute selection measure? 7M 2 L4
Explain.
b) Discuss the model over-fitting. 8M 2 L2
3 a) Explain decision tree classification with suitable 7M 2 L4
example.
b)Write the process of classification by support 8M 2 L1
vector machines when data is both linearly
separable and inseparable.
4 a) Explain the KNN classification. 7M 2 L4
b)What is Bayes theorem? Explain Naïve Bayes 8M 2 L4
classification with suitable example.
5 Explain about SVM? 7M 2 L1
Explain about Evaluating the performance of 8M 2 L1
classifier?
6 a)Differentiate between prediction and 7M 2 L2
classification. And also explain various regression
based methods.
b)Explain the following regressions 8M 2 L4
i) Linear regression
ii) Multiple linear regression
iii) Nonlinear regression.
7 Explain about Separableand Non Separable 7M 2 L1
case.?

How to Evaluating the performance of classifier? 8M 2 L4

 UNIT-III

Knowledge
S.N Marks CO
Question Level
O
1 a) Explain whether association rule mining is 7M 3 L1
supervised or unsupervised type of learning
b) Discuss the F-P Growth Algorithm with an 8M 3 L2
example
2 a) Discuss the importance of Association Rule 7M 3 L2
Mining.
b) Write short notes on 8M 3 L1
i) Frequent item sets.
ii) Closed Item sets.
3 a) Define Frequent sets, confidence, support 7M 3 L3
and association rule.
b) Explain the process of mining multilevel 8M 3 L4
association rules.
4 a) List all frequent item sets and strong 8M 3 L3
association rules with support ‘s’ andconfidence
’c’ for the following transaction database
I1:{T1,T4,T5,T7,T8,T9}, I2=
T1,T2,T3,T4,T6,T8,T9}
I3={T3,T5,T6,T7.T8.T9} I4={T2,T4}
I5={T1,T8}
b) Explain the process of Handling Categorical 7M 3 L4
attributes in data association,
Continuousattributes,
5 a) Can we design a method that mines the 8M 3 L4
complete set of frequent item sets without
candidate generation? If yes, explain with an
example
b) ) Explain the process of Continuous 7M 3 L4
attributes in data association
6 a)Explain about Frequent Item-set generation?
b)Explain whether association rule mining is
supervised or unsupervised type of learning.

7 a)Discuss the importance of Association Rule Mining. 8M 3 L3

b)Explain about FP-Growth Algorithms 7M 3 L1

 UNIT-IV

Knowledge
S.N Marks CO
Question Level
O
1 a) Explain how partitioning clustering works 7M 4 L4
with k-means and k-medoids algorithm
b) Classify various Clustering methods. 8M 4 L1
2 a) Compute Euclidean, Manhattan, Minkowski 7M 4 L2
distance(q=3) between 2 objects for
the given 2 objects represented by tuples
(22,1,42,10) and (20,0,36,8)
b) What is the drawback of k-means algorithm? 8M 4 L1
How can we modify the algorithm to diminish?
that problem?
3 a) What is cluster analysis? Explain the typical 7M 4 L1
requirements of cluster Analysis.
b) Explain the following Grid based clustering 8M 4
methods:i) STINGii) Wave Cluster.
4 a) Differentiate between agglomerative and 7M 4 L1
hierarchical clustering.
b) How does the PAM algorithm work? Explain 8M 4 L4
5 a)Explain DBSCAN. Prove that in DBSCAN, the 7M 4 L4
density-connectedness is an equivalence relation.
b) How to cluster the high dimensional data? 8M 4 L4
Explain various algorithms in it.

6 Explain about Clustering Methods in Data Mining? 4 L1

Disscuss about Centroid-based Clustering 4 L3

Algorithms in Data Mining?
7 What are the Data Mining Algorithms 7M 4 L1
Techniques?

Explain about DBSCAN? 8M 4 L1

 UNIT-V

Knowledge
S.N Marks CO
Question Level
O
1 a) What is anomaly detection? 7M 5 L1
b) Why anomaly detection is important? 8M 5 L2
2 a)Write About Anomaly Detection Algorithm 7M 5 L3
Techniques
b) What are anomalies / outliers and types of 8M 5 L3
anomalies in time-series data?
3 a)Design principles of anomaly detection 7M 5 L4
b)Why your company needs anomaly detection 8M 5 L3
4 a)How Does Anomaly Detection Work? 7M 5 L3
b)What are the functions of Anomaly Detection 8M 5 L1
in Machine Learning
5 a) How Does VMware NSX Advanced Load 7M 5 L4
Balancer Help With Anomaly Detection?
b)What do you think of the relationship between 8M 5 L2
time-series analysis and anomaly detection?
6 a)Why anomaly detection is important? 7M 5 L2

b) Explain about Semi-supervised anomaly 8M 5 L1

detection

7 a)Write about Advantages of Using an Anomaly 7M 5 L3

Detection Algorithm

b)What are the Characteristics of Anomaly 8M 5 L3

Detection Problem