You are on page 1of 3

DMW(PE)-Super Important questions

By the TIE review team-SVIT and BNMIT

Module-1

1. Define the data warehouse and state its key features and give examples
2. Explain in detail the different categories of data cube measures with examples
for each
2b. Explain and solve data cube computation and curse of dimensionality
3. Construct and Explain with an ex(if necessary) (i)KDD process in DM (ii)Fact
constellation schema (iii)Star Schema (iv)Snowflake Schema
4. Build Multi/three-tier architecture and explain in detail with examples
5. Explain the concepts of OLTP and OLAP systems with their key features
6. Identify and solve data cube operations with ex

Module-2

1.Solve cosine similarity for Vectors X and Y, where X= {3 2 0 5 0 0 0 2 0 0} Y= {


1 0 0 0 0 0 1 0 2 1}
2. Identify similarity and dissimilarity between objects, Apply SMC and Jaccard's
coefficient of Two binary vector X={ 1 0 0 0 0 0 0 0 0 0} Y= { 0 0 0 0 0 0 1 0 0 1}
3. Write a short note on (i)Data quality and (ii)Data mining tasks (iii)Data
preprocessing techniques (iv)Challenges- DM
4. Explain the techniques of efficient data cube computation and explain
group-by’s in detail
5. Explain indexing in OLAP data(Bitmap index)
6. Explain the purpose of efficient processing of OLAP Queries

Module-3

1. Analyse association Analysis with apriori algorithm in detail using examples


2. Analyse and explain in detail association rule, support and confidence, inspect
for the following with support - 50%
TID 100 200 300 40
Items {1,3,4} {2,3,5} {1,2,3,4} {2,5}
3. Examine the FP growth algorithm for the following data set with FP tree
construction and explain each step

4. Explain in detail the evaluation of association patterns, and Explain the


approaches for incorporating biased knowledge into the pattern discovery task
5. What are the methods for generating frequent itemsets, Explain
6. What is Correlation analysis? Also, explain Lift with an example.

Module-4

1. With the help of a block diagram analyse the general approach to solve the
classification problem with an example, and also explain methods for
comparing classifiers in detail
2. Explain the decision tree with hunt’s algorithm with an example
3. Inspect decision tree induction algo with an ex, and compare the various
measures for selecting the best split
4. Construct and examine rule-based classifier algorithm with example
B. Construct and examine Bayesian classifier algorithm with example
. 5. Analyse the Nearest neighbour classifier algorithm with example
6. Compare RB with CB Methods and explain the characteristics of Naive
Baye’s classifier
Module-5

1. Analyse and explain Agglomerative hierarchical clustering with a Single


link algorithm, explain with example
2. Construct and explain Bisecting K means algorithm with examples
2b. Construct and explain the DBSCAN algorithm with examples
3. State and explain Cluster evaluation and its issues
4. Explain Graph-based clustering with examples
5. Analyse cluster and clusterings and list different types of clusters and
clustering

How we frame these questions:


TIE review team frames these questions by consolidating comprehensively from
the following sources
1. Exercise problems of textbooks/ references
2. Previous year question VTU exam Question paper and MQP
3. Questions by Various HODs and professors in contact with TIE

Questions framed shall follow all Bloom’s learning levels with appropriate
action verbs ensuring coverage of all COs

Notes available for all modules:


https://takeiteasyengineers.com/category/cse-ise/6th-sem-cse-ise/data-mining/

You might also like