F.4. Data Analytics and Business Intelligence

Question 1

What is data analytics?

Answer 1

The process of gathering and analyzing data to discover patterns and draw conclusions in a way that produces meaningful information that can be used to aid in decision-making.

Question 2

What is the primary goal of data analytics?

Answer 2

To provide information about issues that the analyst or manager either knows or knows he or she does not know (known unknowns).

Question 3

What is data science?

Answer 3

A field of study and analysis that uses algorithms and processes to extract hidden knowledge and insights from data.

Question 4

What is the goal of data science?

Answer 4

To provide actionable insights into issues where the analyst or manager does not know what he or she does not know (that is, “unknown unknowns”).

Question 5

What is business intelligence?

Answer 5

The combination of architectures, analytical and other tools, databases, applications, and methodologies that enable interactive access, sometimes in real time, to data such as sales revenue, costs, income, and product data.

Question 6

What are the four phases of the business intelligence process, and what do they lead to?

Answer 6

It involves the transformation of data into information, then to knowledge, and finally to insight.

The insights gained from the use of business intelligence lead to recommendations for the best action to take.

Question 7

What are the four main components of a Business Intelligence system?

Answer 7

• A data warehouse (DW) containing the source data.
• Business analytics tools to mine, manipulate, and analyze the data.
• A business performance management (BPM) component.
• A user interface, usually in the form of a dashboard.

Question 8

Define:

Big Data

Answer 8

Vast datasets that are too large to be analyzed using standard software tools and require new processing technologies.

Question 9

What are the four V’s of Big Data?

Answer 9

• Volume - the amount of data
• Velocity - the speed at which data is generated and changed
• Variety - the diverse forms of data that organizations create and collect
• Veracity - the accuracy of data, the extent to which it can be trusted for decision-making

Question 10

What is the difference between structured, unstructured, and semi-structured data?

Answer 10

• Structured data: Organized format, suitable for relational databases.
• Unstructured data: No defined format, text-heavy.
• Semi-structured data: Some format, not fully organized in relational databases.

Question 11

What is the purpose of a dashboard in a Business Intelligence system?

Answer 11

To organize and display information relevant to a given objective or process, often with interactive elements for data exploration.

Question 12

What is data mining?

Answer 12

The use of statistical techniques to search large datasets to discover previously unknown, useful patterns, trends, and relationships.

Question 13

What is the main objective of data science?

Answer 13

To extract hidden knowledge and insights from data for forecasting and strategic decision making.

Question 14

What are some general challenges of managing data analytics?

Answer 14

• Data capture
• Data curation (the organization and integration of disparate data collected from various sources)
• Data storage
• Security and privacy protection
• Data search
• Data sharing
• Data transfer
• Data analysis
• Data visualization

Question 15

What is the role of a data scientist?

Answer 15

A professional with skills in statistics, data analysis, machine learning, math, programming, business, and IT, focusing on extracting insights from data.

Question 16

What is the significance of “veracity” in Big Data?

Answer 16

It refers to the accuracy of data, ensuring it is objective and relevant for decision-making and avoiding biased, ambiguous, irrelevant, inconsistent, incomplete, or even deceptive data from being used in analysis, which would result in poor decisions.

Question 17

What is the iterative process in data mining?

Answer 17

The repetition of a process to generate a sequence of outcomes, where each iteration’s outcome is the starting point for the next.

Question 18

What is the difference between data analytics and data science?

Answer 18

• Data analytics focuses on known unknowns.
• Data science aims to provide insights into unknown unknowns.

Question 19

What is the benefit of combining good data and good data science?

Answer 19

They enable data-driven decision-making, leveraging relevant information, transforming data into insights, discovering opportunities, and increasing competitive advantage. They can lead to large productivity gains for a company and the ability to do things it has never done before.

Question 20

What is the primary purpose of data mining?

Answer 20

To create predictions and make inferences about relationships using historical data.

Question 21

What are the basic concepts of predictive analytics?

Answer 21

• Classification
• Prediction
• Association rules
• Online recommendation systems
• Data reduction
• Clustering
• Dimension reduction
• Data exploration
• Data visualization

Question 22

What is classification in predictive analytics in data mining?

Answer 22

Classification involves detrmining which category data belongs to, such as whether a customer will purchase or not purchase. Data is assigned to predefined classes using algorithms to predict what the classification is or will be.

Question 23

What is the difference between classification and prediction in predictive analytics in data mining?

Answer 23

• Classification involves determining which category data belongs to, such as whether customer will purchase or not purchase..
• Prediction involves estimating a continuous numerical value using regression analysis, such as for those who are predicted purchasers, estimating the amount of their purchases (causal forecasting).

Both classification and prediction answer the question, “What will happen?” but classification answers with categories while prediction answers with numbers.

Question 24

What are association rules in predictive analytics in data mining?

Answer 24

They are used to find patterns of association between items in large databases, such as associations among items purchased from a retail store, or “what goes with what.”

Question 25

What is the role of online recommendation systems in predictive analytics in data mining?

Answer 25

To deliver personalized recommendations to users based on collaborative filtering, which generates rules for “what goes with what” at the individual user level.

Question 26

What is clustering in predictive analytics in data mining?

Answer 26

Discovering groups in datasets with similar characteristics without using known structures in the data or fixed groups.

Question 27

What is data reduction in predictive analytics in data mining?

Answer 27

Consolidating a large number of records into a smaller set by grouping them into homogeneous groups.

Question 28

What is dimension reduction in predictive analytics in data mining?

Answer 28

Reducing the number of variables in the data to improve manageability, interpretability, and predictive ability.

Question 29

What is data exploration in predictive analytics in data mining?

Answer 29

Used to understand the data and detect unusual values by examining each variable individually and looking at relationships between and among the variables to discover patterns in the data.

Question 30

What is data visualization in predictive analytics in data mining?

Answer 30

Creating graphics to visualize the distribution of variables and detect outliers (data entries that do not fit into the model because they are extreme observations).

Question 31

What is supervised learning in predictive analytics in data mining?

Answer 31

It is used for classification and prediction. It involves training an algorithm using **labeled data** as the training data. Labeled data contains the outcome value for each record, such as what each customer purchased. ## Footnote After the algorithm has “learned” from the training data, it is tested by applying it to another sample of data for which the outcome is known but is initially hidden (called the **validation data**) to see if it works properly and if it can make predictions that are close to what actually happened. After the algorithm has been thoroughly tested, it can be used to classify data or make predictions from data where the outcome is unknown.

Question 32

What is unsupervised learning in predictive analytics in data mining?

Answer 32

They are trained on data just as supervised learning algorithms are, but the training dataset is **unlabeled**, meaning there are no known outcome variables to predict or classify. Instead, the algorithm discovers patterns, groupings, or structures in the data. ## Footnote Association rules, dimension reduction, and clustering are unsupervised learning methods.

Question 33

What are neural networks in data mining?

Answer 33

They are a machine learning technique used in data mining. Instead of a data scientist needing to manually decide which features matter, a neural network automatically discovers complex patterns and features in the training data.

Question 34

What are the steps in a data mining project?

Answer 34

* Understand the purpose of the project * Select the dataset to use * Explore, clean, and preprocess the data * Reduce data dimension if needed * Determine the data mining task * Partition the data * Select data mining techniques to use * Use algorithms to perform the task * Interpret results of the algorithms and choose the best * Deploy the model

Question 35

What are some challenges of data mining?

Answer 35

* Poor data quality * Information in multiple locations * Biases in data evaluation * Correlation vs. causation (correlation does not prove causation) * Ethical issues such as data privacy * Data security * Unstructured data