Question 1

A query that can be run by an end users and is not programmed in advance is considered a(n)________ query.
A) tailored
B) casual
C) informal
D) ad hoc

Accepted Answer

An ad hoc query is a query that is run on the spot by an end user and is not programmed in advance. This type of query allows users to explore data freely and obtain information that may not have been anticipated or planned in advance.

Question 2

Because the latter steps in the data mining process are built on the outcome of the former ones,one should:
A) start with an understanding of the relevant data.
B) work quickly through the early steps and work in-depth on the latter steps.
C) start by cleaning the relevant data and storing it in a single data warehouse.
D) pay extra attention to the earlier steps in order not to put the whole study on an incorrect path from the onset.

Accepted Answer

It is important to pay extra attention to the earlier steps in data mining as the latter steps are built on the outcome of the former ones. If the earlier steps are not executed correctly, it can put the whole study on an incorrect path from the onset. Therefore, it is necessary to be cautious and thorough in the initial steps to ensure the accuracy and reliability of the final results.

Question 3

The term data mining was originally used to ________. A) include most forms of data analysis in order to increase sales B) describe the analysis of huge datasets stored in data warehouses C) describe the process through which previously unknown patterns in data were discovered D) All of the above

Accepted Answer

Data mining originally referred to the process of discovering previously unknown patterns and insights from large datasets.

Question 4

A good question to ask with respect to the patterns/relationships that association rule mining can discover is "Are all association rules interesting and useful?" In order to answer such a question,association rule mining uses two common metrics ________ and ________.
A) mean; median
B) support; confidence
C) standard deviation; confidence interval
D) regression; distance measure

Accepted Answer

The two common metrics used in association rule mining are support and confidence. Support measures the frequency of the rule in the dataset, while confidence measures the accuracy of the rule based on how often it is true. These metrics are used to determine which rules are interesting and useful, as rules with higher support and confidence are typically considered more valuable.

Question 5

Data mining seeks to identify patterns in the data.All of the following are major types of patterns except:
A) associations
B) regression
C) predictions
D) clusters

Accepted Answer

The major types of patterns in data mining are associations, predictions, and clusters. Regression is a statistical method used to analyze the relationship between variables, but it is not a type of pattern in data mining.

Question 6

Data mining is tightly positioned at the intersection of many disciplines.Those disciplines include all of the following except:
A) management science
B) statistics
C) information systems and databases
D) logistics

Accepted Answer

Data mining is commonly associated with disciplines such as management science, statistics, and information systems/databases. However, logistics is not typically considered one of the key disciplines in data mining.

Question 7

On the commercial side,the most common use of data mining has been in ________ sectors.
A) manufacturing and heath care
B) finance, retail, and health care
C) online retail and government
D) R&D and scientific

Accepted Answer

The most common use of data mining has been in finance, retail, and health care sectors. These industries have large amounts of data that can be analyzed to identify patterns and trends, improve decision-making, and enhance customer satisfaction. Manufacturing and government sectors also make use of data mining, but they are not as widely employed as the finance, retail, and health care sectors. R&D and scientific sectors use data analysis, but data mining is not the most common application in these fields. Online retail is a subset of the retail industry and is included in the B option.

Question 8

Because the data mining is driven by experience and experimentation,depending on the problem situation and the analyst's knowledge,the whole process can be ________ and ________,i.e.,one should expect to go back and forth through the steps quite a few times.
A) simple; iterative
B) expensive; hypothetical
C) time consuming; iterative
D) time-consuming; hypothetical

Accepted Answer

Data mining is a complex process that requires time and iteration to arrive at accurate results. It is time-consuming because it requires the analyst to go back and forth through the steps of the process multiple times until an accurate result is found. Therefore, option C, time-consuming and iterative, is the best choice. Option A is not the best choice because data mining is not a simple process. Option B is not valid because the data mining process does not necessarily require a lot of investment. Finally, option D is incorrect because the data mining process is not hypothetical.

Question 9

In an article in Harvard Business Review,Thomas Davenport (2006)argued that the latest strategic weapon for companies is ________. A) customer relationship management B) e-commerce C) online auctions D) analytical decision making

Accepted Answer

In the article mentioned, Thomas Davenport emphasized the importance of using data and analytics to inform strategic decision-making, making analytical decision making the latest strategic weapon for companies. While customer relationship management and e-commerce can be important tools in a company's strategy, they were not the main focus of Davenport's argument. Online auctions are also not directly related to the concept of a strategic weapon for companies.

Question 10

Business analytics and data mining provided 1-800-Flowers with all of the following benefits except:
A) More efficient marketing campaigns.
B) Increased mailings and response rates.
C) Better customer experience and retention.
D) Increased repeat sales.

Accepted Answer

The use of business analytics and data mining provided 1-800-Flowers with more efficient marketing campaigns, better customer experience and retention, and increased repeat sales. However, there is no mention of increased mailings and response rates being a direct benefit of these techniques.

Question 11

Numeric data represent the numeric values of specific variables,which are ________ variables that can take on an infinite number of fractional values.
A) discrete
B) continuous
C) interval
D) ratio

Accepted Answer

Continuous variables are those which can take on an infinite number of fractional values, such as height or weight. Discrete variables, on the other hand, can only take on a finite number of values (such as the number of children in a family). Interval and ratio variables are subcategories of continuous variables, but they have additional characteristics (such as a true zero point in ratio variables). Therefore, B is the best choice for this question.

Question 12

________ data mining begins with a proposition by the user,who then seeks to validate the truthfulness of the proposition.For example,a marketing manager may begin with the following proposition: "Are BluRay player sales related to sales of HDTV sets?"
A) Hypothesis-driven
B) Theory-driven
C) Discovery-driven
D) Data-driven

Accepted Answer

Hypothesis-driven data mining begins with a specific question or proposition posed by the user. The user seeks to validate or invalidate the hypothesis using data analysis techniques. In this scenario, the marketing manager is posing a hypothesis that BluRay player sales are related to sales of HDTV sets, and will use data mining techniques to test this hypothesis.

Question 13

Predictive analysis uses sophisticated algorithms that can be designed to sift through data and identify ________.
A) patterns of behavior
B) outlier
C) average statistics
D) minimum and maximum statistics

Accepted Answer

Predictive analysis is used to identify patterns of behavior in data. It uses algorithms to analyze historical data and extract trends and patterns that can be used to predict future outcomes. Outliers, average statistics, and minimum and maximum statistics are all types of data points that can be identified through analysis, but they are not the main focus of predictive analysis.

Question 14

Data that has a meaningful,or nonarbitrary,zero point is ________ data.
A) categorical
B) nominal
C) interval
D) ratio

Accepted Answer

Ratio data has a nonarbitrary zero point, meaning that zero represents the absence of the measure being studied. Examples of ratio data include weight, height, and length. Categorical and nominal data do not have a numerical value, and interval data has a meaningful zero point but does not have a true absence of the measure being studied.

Question 15

Why has data mining gained the attention of the business world?
A) More intense competition at the global scale driven by customers' ever-changing needs and wants in an increasingly saturated marketplace.
B) Consolidation and integration of database records, which enables a single view of customers and vendors.
C) Significant reduction in the cost of hardware and software for data storage and processing.
D) All of the above

Accepted Answer

All of the choices are factors that have contributed to the increased attention on data mining in the business world. More competition, consolidated databases, and reduced costs for storage and processing make it more feasible and advantageous for companies to use data mining to gain insights and make better decisions.

Question 16

What is a major characteristic of data mining?
A) Data mining tools are readily combined with spreadsheets and other software development tools.
B) Because of the large amounts of data and massive search efforts, it is sometimes necessary to use serial processing for data mining.
C) Data are often buried within numerous small large databases, which sometimes contain data from several years.
D) The miner needs sophisticated programming skill.

Accepted Answer

Data mining tools are often designed to integrate with other software applications, such as spreadsheets, to facilitate data analysis and reporting.

Question 17

The simple split methodology splits the data into two mutually exclusive subsets called a ________ set and a ________ set.
A) training; test
B) positive; negative
C) holdout; training
D) matrix; test

Accepted Answer

The simple split methodology involves splitting the data into two mutually exclusive subsets called a training set and a test set. The training set is used to build the model, while the test set is used to evaluate the performance of the model on unseen data. Choice A correctly identifies these subsets. Choice B refers to a different concept (positive and negative) and choice C is a variation of the simple split methodology where the holdout set is used for final evaluation after model selection. Choice D is not a commonly used term in the context of machine learning.

Question 18

At the highest level of abstraction,data can be classified as ________ and ________.
A) alpha; numeric
B) categorical; numerical
C) nominal; ratio
D) interval; ration

Accepted Answer

Data can be broadly classified into two types: categorical (also known as qualitative) and numerical (also known as quantitative). Categorical data consists of qualitative variables that can be further classified into nominal and ordinal variables. On the other hand, numerical data consists of quantitative variables that can be further classified into interval and ratio variables. Therefore, option B is the best choice as it covers the highest level of abstraction in the classification of data.

Question 19

________,or supervised induction,is perhaps the most common of all data mining tasks.Its objective is to analyze the historical data stored in a database and automatically generate a model that can predict future behavior.
A) Association
B) Clustering
C) Prediction
D) Classification

Accepted Answer

Classification is a type of supervised learning where the model is trained on historical data to classify new data into predefined categories, making it a common data mining task for predicting future behavior.

Question 20

________ are essentially a hierarchy of if-then statements.They are most appropriate for categorical and interval data.
A) Neural nets
B) Clusters
C) Decision trees
D) Time-series

Accepted Answer

As stated in the question, decision trees are essentially a hierarchy of if-then statements, making them best suited for categorical and interval data. Neural nets and clusters are not hierarchical structures, and time-series data involves predicting values over time rather than identifying categories or intervals.

Quiz 5: Data Mining for Business Intelligence

A query that can be run by an end users and is not programmed in advance is considered a(n) ________ query.

Because the latter steps in the data mining process are built on the outcome of the former ones,one should:

The term data mining was originally used to ________.

A good question to ask with respect to the patterns/relationships that association rule mining can discover is "Are all association rules interesting and useful?" In order to answer such a question,association rule mining uses two common metrics and .

Data mining seeks to identify patterns in the data.All of the following are major types of patterns except:

Data mining is tightly positioned at the intersection of many disciplines.Those disciplines include all of the following except:

On the commercial side,the most common use of data mining has been in ________ sectors.

Because the data mining is driven by experience and experimentation,depending on the problem situation and the analyst's knowledge,the whole process can be and ,i.e.,one should expect to go back and forth through the steps quite a few times.

In an article in Harvard Business Review,Thomas Davenport (2006) argued that the latest strategic weapon for companies is ________.

Business analytics and data mining provided 1-800-Flowers with all of the following benefits except:

Numeric data represent the numeric values of specific variables,which are ________ variables that can take on an infinite number of fractional values.

________ data mining begins with a proposition by the user,who then seeks to validate the truthfulness of the proposition.For example,a marketing manager may begin with the following proposition: "Are BluRay player sales related to sales of HDTV sets?"

Predictive analysis uses sophisticated algorithms that can be designed to sift through data and identify ________.

Data that has a meaningful,or nonarbitrary,zero point is ________ data.

Why has data mining gained the attention of the business world?

What is a major characteristic of data mining?

The simple split methodology splits the data into two mutually exclusive subsets called a set and a set.

At the highest level of abstraction,data can be classified as and .

________,or supervised induction,is perhaps the most common of all data mining tasks.Its objective is to analyze the historical data stored in a database and automatically generate a model that can predict future behavior.

________ are essentially a hierarchy of if-then statements.They are most appropriate for categorical and interval data.