Deck 11: Data Mining and Data Visualization

Question 1

Data mining is a set of activities used to find new, hidden, or unexpected patterns in data.

Answer 1

True

Question 2

A synonym for data mining is information sifting and discovery (ISD).

Answer 2

False

Question 3

Data mining is a business solution, not a technology.

Answer 3

False

Question 4

One of the primary reasons for the rise in data mining popularity is the ever-increasing volume of data that require processing.

Question 5

The broad category of software decision-making technology that enables multidimensional analysis is referred to as OLAP.

Question 6

ROLAP organizes and analyzes data as an n-dimensional cube. The ROLAP cube can be conceptually thought of as a common spreadsheet with two extensions: (1) support for multiple dimensions and (2) support for multiple concurrent users.

Question 7

One of the primary advantages of ROLAP versus MOLAP is it results in performance improvements for data access.

Question 8

MOLAP provides support for concurrent users.

Question 9

Sparcity can significantly increase the storage requirements of a MOLAP hypercube by requiring that space be allocated for all cells rather than just the ones that contain data values.

Question 10

MOLAP is well-suited to handle large numbers of detailed data.

Question 11

ROLAP databases typically contain both summary and detail data.

Question 12

The ROLAP structure contains a large number of normalized tables.

Question 13

The central table in a star schema is a dimension table.

Question 14

Data mining methods can be classified in two ways: by the function they perform or by their class of application.

Question 15

The classification approach to data mining searches all details or transactions from operational systems for patterns with a high probability of repetition.

Question 16

The association approach to data mining is intended to discover rules that define whether an item or event belongs to a particular subset of data.

Question 17

The sequencing approach to data mining relates events in time, based on a series of preceding events.

Question 18

The clustering approach to data mining is useful when there is a need to create partitions in order to discover patterns in the data.

Question 19

Data mining does not use statistical techniques because the complex patterns in data do not lend themselves to linear regression analysis.

Question 20

Two new categories of data mining are text mining and Web mining.

Question 21

Which of the following is not true of data mining?

A) Data mining has seen explosive growth in the area of customer relationship management.
B) Data mining is a business solution.
C) Data mining is a technology.
D) None of the above are true.

Question 22

The set of activities used to find new, hidden, or unexpected patterns in data is referred to as:

A) data warehousing.
B) data mining.
C) data transformation.
D) data aggregation.

Question 23

Which of the following is a reason for the growth in popularity of data mining?

A) Increased volume of data
B) Increased awareness of the inadequacy of the human brain to process multifactorial dependencies or correlations
C) Increased affordability of machine learning
D) All of the above.

Question 24

The term _________ has been generally agreed to represent the broad category of software technology that enables decision makers to conduct multidimensional analysis of consolidated enterprise data.

A) OLAP
B) MOLAP
C) ROLAP
D) None of the above.

Question 25

____________organizes and analyzes data as an n-dimensional cube. The cube can be thought of as a common spreadsheet with two extensions: (1) support for multiple dimensions and (2) support for multiple concurrent users.

A) OLAP
B) MOLAP
C) ROLAP
D) None of the above.

Question 26

In _____________, the multidimensional database server is replaced with a large relational database server. This "super" relational database will contain both detailed and summarized data thus allowing for "drill down" techniques to be applied to the data sets.

A) OLAP
B) MOLAP
C) ROLAP
D) None of the above.

Question 27

In a ________________, the data are stored as a multidimensional array where each cell in the array represents the intersection of all of the dimensions. Using this approach, any number of dimensions may be analyzed simultaneously and any number of multidimensional views of the data can be created.

A) hyperion cube
B) hypercube
C) stochastic cube
D) correlation cube

Question 28

Which term is used to refer to a basic database operation that links rows of two or more tables by one or more columns in each table?

A) n-cube analysis
B) table link
C) table join
D) None of the above.

Question 29

Which of the following is not considered one of the four major categories of processing algorithms and rule approaches?

A) Classification
B) Association
C) Sequence
D) Principal components analysis

Question 30

Which data mining technique utilizes linkage analysis to search operational transactions for patterns with a high probability of repetition?

A) Association
B) Cluster
C) Sequence
D) Principal components analysis

Question 31

There are some cases where it is difficult or impossible to define the parameters of a class of data to be analyzed. In these cases, _____________ methods can be used to create partitions so that all members of each set are similar according to some metric or set of metrics thus creating a set of objects grouped together by virtue of their similarity or proximity to each other.

A) association
B) linkage analysis
C) sequencing
D) clustering

Question 32

___________________ methods are used to relate events in time, such as the prediction of interest rate fluctuations or stock performance, based on a series of preceding events. Through this analysis, various hidden trends can be discovered that are often highly predictive of future events.

A) Association
B) Linkage analysis
C) Sequencing
D) Clustering

Question 33

Which of the following is not a data mining technology?

A) Statistical analysis
B) Neural networks
C) Decision trees
D) All of the above are data mining technologies.

Question 34

A common example of the use of association methods where a retailer can mine the data generated by a point-of-sale system, such as the price scanner you are familiar with at the grocery store is referred to as:

A) sequencing.
B) linkage analysis.
C) clustering.
D) market basket analysis.

Question 35

The process by which numerical data is converted into meaningful images is referred to as:

A) data mining.
B) data warehousing.
C) data visualization.
D) data aggregation.

Question 36

Which of the following is not an advantage of market basket analysis?

A) Identifying which products sell together can help manage inventory.
B) It is more preferable to marketers to market to existing customers.
C) Market basket analysis can sometimes produce results that are due to prior marketing campaigns.
D) All of the above are advantages.

Question 37

An orderly hierarchy of items and item categories that divides each item into a basket analysis is referred to as a:

A) cluster analysis.
B) taxonomy.
C) multi dimensional market basket analysis.
D) None of the above.

Question 38

Which of the following is a limitation of data mining?

A) Identification of missing data
B) Data noise
C) Missing values
D) All of the above.

Question 39

What are Codd's twelve rules for OLAP?