Domain I – Business Acumen – Section C: Data Analytics

Question 1

Data Analytics

Answer 1

is the process of identifying, gathering, and analyzing data with the objective of producing meaningful information and improving the decision‐making process.

Question 2

Structured data

Answer 2

is understandable and organized in a format that allows for repeatable analysis and queries (e.g. operational, customer or financial data)

Question 3

Unstructured data

Answer 3

is not organized into traditional data structures. It exists in a free format that makes analysis much more difficult (e.g. call center communications, documents and texts, social media data (Facebook or Twitter), audio, videos, and images data)

Question 4

Big data

Answer 4

is a term used to describe large, complex data sets that are beyond the capabilities of traditional data processing and analyzing applications.
=> Structured and unstructured data created by individuals, organizations, applications, smart machines, sensing devices, and Internet of Things (IoT) are growing rapidly.

Question 5

Volume

Answer 5

the amount of data being created, captured and processed is vast compared to traditional data sources. Data analytics infrastructure must be appropriate to handle such greater amounts of data.

Question 6

Varity

Answer 6

Data is being generated by increasing number of sources with different formats.
=> To be successful, data analytics must take into account all types and formats of data.

Question 7

Velocity

Answer 7

Data is being produced at extremely increasing speed. => To add value, data analytics must focus on critical data elements that are relevant to the objectives.

Question 8

Veracity

Answer 8

Data must faithfully reflect the truth. For analytical purposes, the data must be cleaned and normalized in order to limit the possibility of inaccuracy and errors. A strong data governance culture contributes to the veracity of data.

Question 9

Data governance

Answer 9

is the management of the data used by an organization to ensure its quality, availability, usability, integrity, consistency, and security.

Question 10

The Five Steps of Data Analytics Process

Answer 10

1. Define the Question
2. Obtain the Data
3. Clean and Normalize the Data
4. Analyze the Data
5. Communicate the Results

Question 11

Cleaning (or cleansing) the data

Answer 11

refers to the process of detecting incomplete,

corrupt, incorrect, inaccurate or irrelevant elements of the data and then correcting or removing those elements.

Question 12

Normalizing the data

Answer 12

refers to the process of restructuring or organizing the data in order to reduce data redundancy and improve its usability. Data elements that are unexpected, peculiar, nonconforming, or not easily classified are identified and corrected or removed.

Question 13

Descriptive Analytics

Answer 13

What happened? Descriptive analytics answers the question of what has happened.
= > Examples of descriptive analytics include examining all payments to vendors to identify payments without a valid purchase order.

Question 14

Diagnostic Analytics

Answer 14

Why something happened? Diagnostic Analytics answers the question of why something has happened. It gives a deep insight into a particular problem or event to identify its cause and uncover possible dependencies and patterns.
=> Examples of descriptive analytics include examining authorization and other controls over the paying process to identify why there are payments to vendors without a valid
purchase order.

Question 15

Predictive Analytics

Answer 15

What might happen? Predictive analytics is based on analyzing current data and providing certain assumptions to draw valid correlations and predict
future outcomes and trends.
=> For example, collecting and analyzing data on buying trends may enable the analyst to predict future changes and risks in the demand.

Question 16

Prescriptive Analytics

Answer 16

What actions to take? Prescriptive analytics seeks to determine the actions that will produce the best result in the light of predictive analytics forecasts.
=> For example, predictive analytics may determine the future changes in the demand, while prescriptive analytics determines the actions required to minimize the risks and maximize the benefits of those expected changes in the demand.