DOEACC Society 2006 DOEACC C Level CE3 - Data Warehousing & Mining( ) - Question Paper

CE3-R3: DATA WAREHOUSING AND DATA MINING
NOTE:
Time: three Hours Total Marks: 100
1.
a) define the differences ranging from the subsequent architectures for the integration of a data
mining system with a database or data warehouse system: no coupling, loose coupling,
semi-tight coupling, and tight coupling. Also mention which architecture is the most
popular 1 and why.
b) explain different kinds of concept hierarchies by providing 2 examples for every type?
c) explain the differences ranging from canned queries and ad hoc queries.
d) Illustrate the typical requirements of clustering data mining.
e) State different valuation criteria that are essential for classification and prediction
methods.
f) elaborate the difficulties that can arise with hieratical clustering?
g) State the differences ranging from data quality and data accuracy.
(7x4)
2. Suppose that a data warehouse consists of 4 dimensions date, spectator, location,
and game, and the 2 measures count and charge, where charge is the fare that a
spectator pays when watching a game on a provided date. Spectators may be students,
adults, or seniors. With every category having its own charge rate.
a) Draw a star schema diagram for the data warehouse.
b) How many cuboids are needed to build the data cube? List them
c) Starting with base cubiod, what specific OLAP operations should 1 need to perform in
order to list the total charge paid by learner spectators at New Delhi in the year 2004?
(6+6+6)
3.
a) elaborate the advantages and limitations of snowflake schema design?
b) What is meant by data reduction? explain any 2 data reduction strategies for
obtaining a decreased data representation.
(9+9)
4.
a) What does hierarchical clustering mean? In what way it is various from partition-based
methods.
b) explain the functionality of Chameleon’s clustering method with an example.
c) What is concept hierarchy? discuss its importance in Data Mining.
(6+8+4)
CE3-R3 Page one of two January, 2006
1. ans ques. one and any 4 ques. from two to 7.
2. Parts of the identical ques. should be answered together and in the identical
sequence.
5.
a) provide an example to show that items in a strong association rule may truly be negatively
correlated.
b) What is meant by Multi level association rule? explain any 2 approaches for mining multi
level association rules with examples.
(6+12)
6.
a) explain how to develop an efficient implementation of data mining system for mining weblog
access sequences.
b) An e-mail database is a database that stores a large number of electronic mail messages.
Such a database is 1 type of semi-structured database consisting of textual data.
i) How can you structure such an email database in order to facilitate
multidimensional search.
ii) What can be mined from such an email database?
iii) Suppose email messages were classified as junk, unimportant, normal or
important, defines how a data mining system may take this as the training set
to automatically classify new email messages or unclassified ones.
(6+12)
7.
a) describe a spatial data cube. explain various kinds of dimensions in a spatial data cube.
b) State the salient differences ranging from data query and knowledge query?
c) An object cube can be constructed by generalization of an object-oriented database into
relatively structured data prior to performing multidimensional generalization. explain
how to handle set-oriented data in an object cube.
(5+5+8)
CE3-R3 Page two of two January, 2006

Earning:   Approval pending.