1
Seat No.: Enrolment
GUJARAT TECHNOLOGICAL UNIVERSITY
ME SEMESTER- I • EXAMINATION SUMMER 2018
Subject Code:2712309 Date: 10/05/2018
Subject Name: Data Mining
Time: 02:30 PM to 05:00 PM Total Marks: 70
Instructions:
1. Attempt all questions.
2. Make suitable assumptions wherever necessary.
3. Figures to the right indicate full marks.
Q.1

List out the different schema of data warehouse and explain one of the data warehouse schemas in detail with suitable diagram.
07

Compare frequent item set generation using FP growth algorithm with Apriori algorithm.
07
Q.2

Define the term "Data Mining". With the help of a suitable diagram explain the process of knowledge discovery from databases
07

What is data cleaning? Describe the different methods of handling missing values during data cleaning
07
OR

What is data transformation? Explain the different data transformation approaches for transforming data.
07
Q.3

What is Concept Hierarchy? List and explain different types of Concept Hierarchy.
07

What is an How do outliers impact the results of mining? Explain any one method to detect outliers.
07
OR
Q.3

State the Apriori Property. Generate large itemsets and association rules using Apriori algorithm on the following data set having minimum support value as 2 and minimum confidence value as 75%.
TID
Items Purchased
T101
Cheese, milk, cookie
T102
Butter, milk, bread
T103
Cheese, butter, milk, bread
T104
Butter, bread
07

Explain methods for data normalization for age values as: 13, 15, 16, 16, 19, 20, 23, 29, 35, 41, 44, 53, 62, 69, 72. Transform age value 45 for all methods.
For min-max normalization consider range as 1.0].
For z-score normalization standard deviation of age is 20.64 years.
For decimal scaling make necessary assumption.
07
Q.4

What is supervised and unsupervised learning? What is Cluster Analysis? List and explain requirements of clustering in data mining.
07

Explain with example how continuous numerical data values can be discretized.
07
OR
Q.4

Write steps of K-Means clustering algorithm with its pros and cons. How K-Mean clustering method differs from K-Medoid clustering method?
07

Explain the following attribute selection measures for decision trees:
Information Gain Gain Ratio
07
Q.5

List and explain various OLAP operations.
07
2

What is time series database? How to characterize the time series data using trend analysis?
07
OR
Q.5

Explain different types of web mining with suitable example.
07

Discuss the characteristics and limitations of Neural Networks. Mention any two suitable applications of neural networks.
07