Vous êtes sur la page 1sur 2

1a.

Define data warehouse


b. Compare OLTP with OlAP
c. Discuss the 3 main types of data warehouse usage: information processing,
analytical processing and data mining.
d. Draw a star schema of a data warehouse for sales containing sales fact table and
dimension tables for time, item,branch and location.

2 a. Discuss the various methods for handling missing values.


b. Describe the various techniques for data transformation.
c. In a data analysis problem we have an attribute age. The age values for the data
tuples are(in increasing order)
13,15,16,16,19,20,20,21,22,22,25,25,25,25,30,33,33,35,35,35,35,36,40,45,46,53 and
70
i. Use min-max normalization to transform the value 35 for age onto the range
[0.0,1.0]
ii. Use z-score normalization to transform the value 35 for age where the
standard deviation of age is 12.94 yrs.

3 a Discuss the various data mining primitives by means of examples.


b. What are 1) No coupling
2) loose coupling
3) semi tight coupling
4) tight coupling
in data mining environment?

4 a. Discuss the apriori algo by means of an example.


b. we are given the following set of 4 transactions in market based model.

Transaction –id Items bought


104 Milk, bread, cookies, juice
792 Milk juice
1130 milk eggs
1735 bread cookies

Build a frequency pattern (FP) tree.

5 a. Differentiate between classification and prediction.


b. Give an example of Bayesian Belief Networks.
c. Discuss the working of back propagation algorithm in terms of various steps.
D Give the table for X(yrs of exp) and Y(corresponding salary of engineers in rs)
predict the salary of the engineer with 12 yrs experience using linear regression
technique.
X Y
1 20
3 36
6 43
3 57

6 a . What is clustering?
b. Discuss density based methods of clustering.
c. Given 2 object represented by tuples (22,1,42,10) and (20,0,36,8) following
1. Euclidean distance between the 2 objects
2. Manhattan distance between the 2 objects
3. Minkowski distance between the 2 objects using the power q=3.

7 a . What are the requirements of clustering in data mining?


b. Briefly describe any of the following approaches to clustering methods:
Partitioning methods or hierarchical methods giving examples wherever
necessary.

8a. Discuss data mining applications either for


1. financial data analysis OR
2. telecommunication industry
b. Describe the trends In data mining.

Vous aimerez peut-être aussi