NEW
Font size
WorksheetsEBDP
Total questions: 60
Worksheet time: 30mins
Which is one of the four characteristics of Big Data?
Validity
Volume
Value
Variability
Which is one of the primary reasons that so many organizations find it difficult to realize a competitive advantage through Big Data?
They treat information as a strategic asset
All of their Big Data is actively being used
They have not adequately defined a Big Data strategy
They compete on the preciseness of their data
What type of skew is indicated when most values in a data set are greater than the mean?
Major
Minor
Positive
Negative
What techniques are commonly associated with supervised machine learning?
Classification and correlation
Correlation and regression
Classification and regression
Regression and clustering
Which of the following statements apply to structured data?
1. Is organized in a pre-defined format or table
2. Is typically stored in Excel files or SQL databases
3. Is typically text heavy, but may also contain dates, numbers and facts
4. Shows where relationships are established between fields
1, 2, 3
1, 2, 4
1, 3, 4
2, 3, 4
Having completed a few simple Big Data projects, an organization now wants to ensure their Big Data Team retain their Big Data knowledge and adopt a culture of continuous learning.
Achieving which organization success factor would MOST support this?
A clear view of what the organization is aiming to achieve with Big Data
Effective data governance and data management processes
A centralized Big Data Centre of Excellence
An ongoing Big Data professional training program
For the analysis of which kind of data are Deep Learning techniques predominantly used for?
Categorical and random
Alpha and numeric
Images and audio
Machine and integer
What level on the Big Data maturity scale is demonstrated by an organization that is managing data and analytic capabilities across all domains of the organization but has yet to fully optimize all its Big Data activities?
Level 2 – Localized Analytics
Level 3 – Analytical Operation
Level 4 – Analytical Enterprise
Level 5 – Data Driven Enterprise
What differentiates cognitive analytics from other forms of analytics?
Decisions are made based on the perceived environment and personalized characteristics
General awareness and emotional intelligence are factored into the decision process
Rationale perception and a generalized set of conditions are factored into the decision process
Decisions are automated and irrelevant of any individual preferences
When formulating a Big Data strategy, in what sequence should the following occur?
1. Define business objectives
2. Identify and prioritise Use Cases
3. Execute a current state assessment
4. Formulate a Big Data Roadmap
1, 3, 2, 4
1, 3, 4, 2
3, 1, 2, 4
3, 2, 4, 1
What effect does Big Data have on data samples used to make predictions?
Smaller subsets of data are required for results
Sample sizes are closer to the entire population
Relationships are created between all data samples
Samples become independent of populations
Which statement BEST describes a reference architecture?
A set of documents to which a project manager or other interested party can refer for best practices
A source of information configured using a common structure within a computer
A piece of shared advice that builds upon common knowledge gained by others
A recommendation based on a standard design principle that others have experience of
According to the Big Data Framework, what is the definition of Big Data?
The grouping of bulky information that cannot be processed manually or through automated computer software
The creation of computer programs that are able to process large quantities of data
The consolidation of internal, external, structured, semi-structured, unstructured and enterprise data
The exploration of techniques, skills and technology to deduct valuable insights out of massive quantities of data
What are solid stated drives (SSD), optical disk devices or external hard drives that are connected to a computer examples of?
Storage Area Network (SAN)
Network Attached Storage (NAS)
Direct Attached Storage (DAS)
Direct Area Network (DAN)
Which of the following is one of the five main roles within the NIST Big Data Reference Architecture?
Data Manufacturer
Digital Analyst
Data Provider
Dialogue Provider
What type of analysis could be used to explore whether a relationship exists between the amount of vitamins a subject group take and their life span?
Clustering
Sampling
Correlation
Regression
Which characteristic applies to data sets in Big Data?
Contains a percentage of meaningless details
Are generated from a single source
Are presented in one common structure
Exploit traditional storage capabilities
Which of the following are key characteristics of a well-designed Big Data Lab?
1. Open work space for collaboration
2. Isolated work space without distractions
3. Creative environment to experiment
4. Networked computers with 4GB RAM
1, 2, 3
1, 2, 4
1, 3, 4
2, 3, 4
An insurance company wants to use the character profile of a sample of its existing customers to determine the most effective advertising media to use for a new insurance product.
What type of business objective would address this need?
Descriptive business objective
Inferential business objective
Predictive business objective
Mechanistic business objective
How does Hadoop overcome the risk of losing data that is being stored or processed?
Includes a system for backing up entire machines to a central database multiple times each day
Uses parallel programming models to reduce the risk of losing data during processing
Uses Storage Area Networks (SANs) to enhance storage devices
Replicates data packages and stores them on a number of different machines
An analysis of 200,000 candidate’s test results shows that 99.9% of candidates scored between 76% and 89%. There were 18 candidates who scored less than 20%.
What statistical term is used to describe these anomalies?
Outliers
Random data points
Deviations
Multivariate observations
Identify the missing word in the following sentence.
A Big Data [ ? ] is required to help focus an organization’s investment in Big Data analysis and analytics.
Strategy
Architecture
Team
Function
Which statement does NOT apply to Hadoop?
Is an open source software framework used for processing datasets of Big Data
Consists of modules designed on the assumption that hardware failures rarely occur
Assumes that hardware failures should be automatically handled by the framework
Has become known as the eco-system that connects different Big Data solutions
4,000 students completed an examination paper across the country. These results need to be communicated to all examination centres.
What type of graphical representation would show the highest and lowest scores, the average score, the upper and lower quartile, and any individual scores that do not fit within the general pattern of others?
Scatter plot
Biplot
Box plot
Q-Q plot
Which of the following is a benefit of using an ‘open’ Big Data reference architecture?
Guarantees fast and accurate results analysis of raw data
Supports the use of ever changing solutions to solve similar problems
Non-restrictive and open to interpretation in terms of application
Provides a common language for stakeholders
Within the data management process, which of the following statements about the data improvement and validation activity of the data management process is/are true?
1. The objective is to reduce errors in data sets.
2. It triggers an alert if any corrupt data is detected.
a) Only 1 is true
b) Only 2 is true
c) Both 1 and 2 are true
d) Neither 1 or 2 is true
What type of statistic quantitatively describes or summarizes the features of a collection of information?
Descriptive
Summary
Expressive
Explanatory
What data governance activity determines the policies for how an organization’s external contractors should manage data access, retrieval, storage, destruction and back up, to ensure management and protection of data is maintained?
Develop quality strategy
Review regulatory and privacy requirements
Develop data governance policies
Assign roles and responsibilities
Which of the following is NOT a core component in the Hadoop Architecture?
NameNode
MapReduce
Slave Node
Job Seeker
In dispersion statistics, what is indicated by a high standard deviation for a set of data values?
Data entries are all very good quality
Values are close to those expected
Data is spread out over a wide range
Values are clustered near to the average
What step in the data analysis process would use a look-up table to cross-reference and correct any area codes that have been entered in the wrong format?
Data identification
Data collection and sourcing
Data review
Data cleansing
Why is skewness important in data science?
Highlights potential for errors in predictions
Establishes limits for deviations from the mean
Allows multiple data sets to be combined
Presents results from several different angles
What type of analytics should be used by a manufacturing company to understand why a certain product performs well in the South East Asia market?
Descriptive analytics
Diagnostic analytics
Predictive analytics
Prescriptive analytics
How is the data identification graph used in the data analysis process?
To collect data from various sources and determine the value of the data
To determine whether there are any problems or issues in the data set
To determine if the data set contains missing values
To identify where the raw data might be obtained
In what sequence did the following capabilities of Big Data evolve over time?
1. Location-aware and person-centred analysis
2. Data mining and statistical analysis
3. Web analytics and web intelligence
1, 2, 3
2, 1, 3
2, 3, 1
3, 2, 1
Which of the following statements about Big Data analysis architecture is/are true?
1. Offline analysis is more expensive than real-time analysis.
2. Offline analysis enables multiple batches of data to be processed concurrently.
Only 1 is true
Only 2 is true
Both 1 and 2 are true
Neither 1 or 2 is true
What measures are used to prioritize Use Cases when formulating a Big Data strategy?
Level of business involvement and stakeholder buy in
Current performance against predefined measures for success
Number of user groups affected, and the data sources required
Anticipated benefit to users and capability to implement
Temperatures (0°c) recorded in London over a week in June are shown in the table below. The mean temperature during this period was 19°c.
What measure is represented by the value 3.4?
a) Range
Interquartile Range
Variance
Standard Deviation
What is the purpose of a Job Tracker within the Hadoop framework?
To follow directions for processing jobs
To initiate and coordinate processing jobs
To keep track of where data is located
To load and analyze the final result
A bank has decided to formulate a Big Data strategy following the steps outlined in the Big Data Framework. They have identified several potential Use Cases where Big Data might provide long-term strategic value to the organization. 27 Use Cases have been identified, which is more than the organization can accommodate in terms of budget and resources.
What would be the BEST next step to take?
Review and prioritize every Use Case based on business impact, budget and resource requirements
Formulate a Big Data Roadmap to identify which projects will be executed first
Execute a current state assessment to help align the Use Cases to current business goals
Find correlations across multiple data sources to identify which Use Cases are most feasible to execute
What distribution shape would show how likely it is a customer will buy a new product after an email campaign?
Frequency
Probability
Sampling
Normal
A high resolution X-ray of a patient’s broken bone also includes data on the patient’s name, date of birth and patient number. What is the date of birth an example of?
Data bias
Data visualization
Metadata
Unstructured data
Identify the missing words in the following sentence. The statistical process of standardization is important in Big Data because it makes it possible to [?] within a data set.
eliminate bias
identify relationships
compare multiple variables
identify outliers
Which of the following statements is/are true?
1. Correlation estimates the effect of independent variables on the dependent variable in order to make predictions.
2. Regression explores the reason why one variable causes a change in another variable.
a) Only 1 is true
b) Only 2 is true
c) Both 1 and 2 are true
d) Neither 1 or 2 is true
What sort of algorithm could be used to give a diagnosis to a patient based on observed symptoms?
Calculation
Correlation
Clustering
Classification
Which of the following statements about the differences between local and distributed storage solutions is/are true?
1. Business Intelligence analysis tools are best suited to distributed storage solutions.
2. For data held in local data storage solutions it is more appropriate to use analytics and visualization tools.
Only 1 is true
Only 2 is true
Both 1 and 2 are true
Neither 1 or 2 is true
What do classification algorithms do?
Indicate whether a relationship exists between variables
Group sets of objects based on similarities in their characteristics
Identify which known category a new observation belongs to
Condense large data sets into summary graphs
What do clustering algorithms do?
Indicate whether a relationship exists between variables
Group sets of objects based on similarities in their characteristics
Identify which known category a new observation belongs to
Condense large data sets into summary graphs
In a distributed storage system, what has been developed to speed up access to data stored across thousands of servers?
File systems
NoSQL Databases
Parallel programming models
Direct Attached Storage (DAS)
Which of the following statements is/are true?
1. The primary purpose of data analysis is to review existing data in order to support decisionmaking.
2. The primary purpose of analytics is to analyze data sets in order to optimize the future.
Only 1 is true
Only 2 is true
Both 1 and 2 are true
Neither 1 or 2 is true
Which of the following is NOT one of the six main elements within the Big Data Framework?
Big Data Architecture
Big Data Algorithms
Big Data Methodologies
Big Data Strategy
What class of machine learning is used by a website recommendation engine to suggest to an online customer additional products for purchase as they move to the payment screen?
The suggestions are based on profiles of other customers who have made similar purchases.
Structured
Supervised
Unsupervised
Unstructured
What is the function of the System Orchestrator within the NIST Big Data Reference Architecture?
Introduce new data or information feeds into the Big Data system
Ensure that the components of Big Data environments work together
Use business logic and functionality to transform data into the desired results
Store and process data based on designs that are optimized for Big Data
What Big Data process covers the assignment of roles and responsibilities for maintaining a consistent and proper handling of data across the business?
Data analysis
Data management
Data governance
Data organization
Which Big Data Team role needs the ability to come up with creative ideas to help them design and develop algorithms?
Big Data Analyst
Big Data Scientist
Big Data Engineer
Big Data Architect
In Artificial Intelligence, which essential capability exploits the outcome from studies about how humans deal with problems in order to model reasoning?
Automated reasoning
Knowledge representation
Machine learning
Natural language processing
What is correlation?
A causal relationship between two data sets
The conversion of data points to a standardized value
A statistical relationship between two random variables
The difference between the largest and smallest values in a data set
In cognitive analytics, what is it that makes decisions and takes specific actions, based on the perceived environment and patterns of specific users?
Intelligent algorithm
Active mediator
Human operator
Rational agent
According to the Turing test, what is used to assess a machines ability to exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human?
Mathematical equations
Scientific algorithms
Written questions
Verbal communication
A fast-growing telco company is looking to build up its Big Data capabilities. Some research has been done into possible approaches to accomplish this. What is the BEST approach that the company can now take?
Hire experienced data scientists from other organizations
Initiate the formation of a Big Data Centre of Excellence
Design processes for Big Data Analysis, Data Management and Data Governance
Identify the most suitable Big Data tool for her organization
