BITS WILP Advanced Data Mining Quiz-1 2018-H1




Question 1
Partition Based Algorithm for frequent pattern mining
Select one:
a. Assumes that globally frequent item-set may not dominate locally at some partitions
b. Assumes that globally frequent item-set may dominate locally at some partitions
c. All of the above
d. Need multiple scans of the database.
Feedback
The correct answer is: Assumes that globally frequent item-set may dominate locally at some partitions
Question 2
Why does the data used in data mining process could be a different version of the original one
Select one:
a. Modified version may be better suited to the knowledge discovery
b. Original data is hard to get and store
c. Some of the portion of the data may be stale and may not be in usable form
d. None of the above
Feedback
The correct answer is: Modified version may be better suited to the knowledge discovery
Question 3
Incremental Association Rule Mining
Select one:
a. Attempts to update the previously obtained result in constant time
b. Attempts to obtain mining result in the time proportional to the changes in database
c. Attempts to update the previously obtained result in time proportional to database size
d. Attempts to update the previously obtained result in time proportional to changes in database
Feedback
The correct answer is: Attempts to update the previously obtained result in time proportional to changes in database
Question 4
Association rules mining
Select one:
a. Mainly focuses research on association rule generation from frequent sets
b. Tries to do a predictive analysis
c. Mainly involves sequence discovery
d. Mainly focuses on frequent item set generation
Feedback
The correct answer is: Mainly focuses on frequent item set generation
Question 5
Data Mining is
Select one:
a. Used for advance data processing.
b. Used to extracting information from data.
c. Used as a tool for KDD
d. Used to discover schema of a data.
Feedback
The correct answer is: Used as a tool for KDD
Question 6
Fast update 2 algorithm is
Select one:
a. An incremental algorithm that can handle insertions in database
b. An incremental algorithm that improves FUP by handling deletion
c. An algorithm that never needs a rescan of the complete database.
d. None of the above
Feedback
The correct answer is: An incremental algorithm that improves FUP by handling deletion
Question 7
Difference between noise and error in data
Select one:
a. There is no difference
b. Error can not be avoided
c. Noise can not be avoided
d. Noise and error both could be avoided
Feedback
The correct answer is: Noise can not be avoided
Question 8
How can "algorithm" improves the data mining 
Select one:
a. None of the above
b. Algorithm gives use handle on its complexity that can used to improve the efficiency of the data mining
c. Algorithm helps us to gather better data
d. Algorithm can specify step by step procedure for knowledge discovery
Feedback
The correct answer is: Algorithm gives use handle on its complexity that can used to improve the efficiency of the data mining
Question 9
Find support for association rule X=>Z in following database

{A,B,Z}
{X,Y,Z}
{A,X,Z}
{B,X,Y}
{X,A,Z}
{Y,A,X}
{Y,B,Z}
Select one:
a. 5/7
b. 4/7
c. 3/7
d. None of above
e. 1/2
Feedback
The correct answer is: 3/7
Question 10
Consider Hash Based Algorithm for frequent pattern mining
Select one:
a. The algorithm is not scalable
b. It reduces effective rescan of the database
c. None of above
d. Choice of hash function is fixed and can not be changed
Feedback
The correct answer is: It reduces effective rescan of the database

No comments:

Post a Comment