Quiz
Modulo 2 - Big Data Analysis & Technology Concepts
Questions in this quiz (200)
1Big Data Analysis
- Adiffers from traditional data analysis primarily because of the volume, velocity and variety characteristics of the data it processes
- BWhen two variables are considered to be _____________ they are considered to be aligned based on a linear relationship
- CThis means that when one variable changes, the other variable also changes proportionally and constantly
- Dthis helps maintain data provenance throughout the big data analysis lifecycle, which helps establish and preserve data accuracy and quality
2step-by-step process
- Ais needed to organize the task involved with retrieving, processing, producing and repurposing data
- Btherefore, it is advisable to store a verbatim copy of the original dataset before proceeding with the filtering. To save on required storage space, the verbatim copy is compressed before storage
- CAlthough the data format may be the same, the data model may be different
- Ddepending on the business scope of the analysis project and nature of the business problems being addressed, the requiered datasets and their sources can be internal and/or external to the enerprise
3Big Data Analysis Lifecycle
- ABusiness Case Evaluation
- BData Identification
- CA/B Testing
- DAn ________ is employed when the comparatively simple data manipulation functions of a query engine are insufficient
4Big Data Analysis Lifecycle
- AData Adquisition & Filtering
- BData Extraction
- Csuggestions commonly pertain to recommending items, such as movies, books, web pages, people, etc.
- Dthe processing engine mechanism will often use the ___________ to coordinate data processing across a large number of servers. This way, the processing engine does not require its own coordination logic
5Big Data Analysis Lifecycle
- AData Validation & Cleansing
- BData Aggregation & Representation
- CThe ______ itself is a visual, color-coded representation of data values
- Dthe processing engine mechanism will often use the ___________ to coordinate data processing across a large number of servers. This way, the processing engine does not require its own coordination logic
6Big Data Analysis Lifecycle
- AData Analysis
- BData Visualization
- CA _______ is generally expressed using a line chart, with time plotted on the x-axis and recorded data value plotted on the y-axis
- DUtilization of Analysis Results
7Business Case Evaluation
- Arequires that a business case be created, assessed and approved prior to proceeding with the actual hands-on analysis task
- Bhelps decision-makers understand the business resources that will need to be utilized and which business challenges the analysis will tackle
- CUnstructured text is generally much more difficult to analyze and search, compared to structured text
- Dis an example of the application of the law of large numbers
8Business Case Evaluation
- Athe further identification of KPI during this stage helps determine how closely the data analysis outcome needs to meet the identified goals and objectives
- Bbased on the business requirements documented, it can be determined whether the business problems being addressed are really Big Data problems
- CApplications for ___________ include fraud detection, medical diagnosis, network data analysis and sensor data analysis
- Dcan be applied to the categorization of unknown documents, and to personalized marketing campaings by grouping together customers with similar behavior
9Business Case Evaluation
- Ain order to qualify as a Big Data Problem, a business problem needs to be directly related to one or more of the Big Data characteristics of volume, velocity or variety
- BNote also that another outcome of this stage is the determination of the underlying budget required to carry out the analysis project
- CThe processing engine enables data to be queried and manipulated in other ways, but to implement this type of functionality requires custom programming
- DWorkflow Engine
10Business Case Evaluation
- Aany required purchase of tools, hardware, training, etc. need to be understood in advance, so that the anticipated investment can be weighed against the expected benefits of archieving the goals
- Binitial iteration of the big data analysis lifecycle will require more up-front investment of Big Data technologies, products and training compared to later iterations where these earlier investment can be repeatedly leveraged
- CIn the context of traditional data analysis, the ______ states that, starting with a reasonably large sample size, the value obtained from the analysis of additional data decreases as more data is successively added to the original sample
- Dcan be applied to the categorization of unknown documents, and to personalized marketing campaings by grouping together customers with similar behavior
11Data Identification
- Ais dedicated to identify datasets (and their sources) required for the analysis project
- Bidentifying a wider variety of data sources may increase the probability of finding hidden patterns and correlations
- CClassification, outlier detection, filtering, natural language processing, text analytics and sentiment analysis can utilize ___________
- DClustering
12Data Identification
- Ait can be beneficial to identify as many types of related data sources and insights as possible, especially when we dont know exactly what we're looking for
- Bdepending on the business scope of the analysis project and nature of the business problems being addressed, the requiered datasets and their sources can be internal and/or external to the enerprise
- Cexamples of appenden metadata can include dataset size and structure, source information, date and time of creation or collection, language-specific information, etc.
- Dis generally used in data mining to get an understanding of the properties of a given dataset. After developing this understanding, classification can be used to make better predictions about similar, but new or unseen data
13Internal Datasets
- Aa list of available datasets from sources, such as data marts and operational systems, are typically compiled and matched against a predefined dataset specification
- BA distributed Big Data solution that needs to run on multiple servers relies on the coordination engine mechanism to ensure operational consistency across all of the participating servers
- CSubsequent to __________ being made available to business users to support business decision-making (such as via dashboard), there may be further oportunities to utilize the __________
- DIn other areas such as the scientific domains, the objective may simply be to observe which version works better in order to improve a process or product
14External Dataset
- Aa list of possible third-party data providers (data markets and publicity available datasets), are generally compiled. Some forms of external data may be embedded within blogs or other types of content-based Websites, in which case they may need to be harvested via automated tools
- Bcan be applied to the categorization of unknown documents, and to personalized marketing campaings by grouping together customers with similar behavior
- CReconciling these differences can require complex logic that is executed automatically without the need for human intervention
- DA big data _________ utilizes a distributed parallel programming framework that enables it to process very large amounts of data distributed across multiple nodes
15Data adquisition & filtering
- Athe data is gathered from all of the data sources that were identified during the previous stage and is then subjected to the automated filtering of corrupt data or data that has been deemed to have no value to the analysis objectives
- Bdepending on the type of data source, data may come as a dump of files (such as data purchased from a third-party data provider), or may require API integration (such as with Twitter)
- CA ________ engine enables data to be moved in or out big data solution storage devices
- DA _________ comprises grouped read/writes, with a larger data footprint consisting of complex joins and high-latency responses
16Data adquisition & filtering
- AIn many cases, especially where external, unstructured data is concerned, some or most of the acquired data may be irrelevant (noise) and can be discarded as par of the filtering process
- Bdata classified as "corrupt" can include records with missing or nonsensical values or invalid data types
- Cit involves plotting entities as nodes and connections as edges between nodes
- DOLTP and operational systems (write-intensive) as well as operational BI and analytics (read-intensive), both fall within this category
17Data adquisition & filtering
- Adata that is filtered out for one analysis may possibly be valuable for a different type of analysis
- Btherefore, it is advisable to store a verbatim copy of the original dataset before proceeding with the filtering. To save on required storage space, the verbatim copy is compressed before storage
- Cis an example of the application of the law of large numbers
- DCoordination Engine
18Data adquisition & filtering
- Aboth internal and external data needs to be persisted once it gets generated or enters the enterprise boundary
- Bfor batch analytics, this data is persisted to disk prior to analysis
- Cextracting text for text analytics, which requires scans of whole documents, will not be necessary if the underlying Big Data solution can already read the document in its native format directly
- Dis dedicated to determining how and where processed analysis data can be further leveraged
19Data adquisition & filtering
- Ain the case of realtime analytics, the data is analyzed first and then persisted to disk
- Bmetadata can be added via automation to data from both internal and external data sources to improve the classification and querying
- CAlso known as offline processing, ________ processing involves processing data in batches and usually imposes delays (resulting in high-latency responses)
- Dis generally applied via the following two approaches: collaborative ____________ and content-based ____________
20Data adquisition & filtering
- Aexamples of appenden metadata can include dataset size and structure, source information, date and time of creation or collection, language-specific information, etc.
- Bit is vital that metadata be machine-readable and passed forward along subsequent analysis stages
- CThe ability to analyze massive amounts of data and find useful insights carries little value if the only ones that can interpret the results are the analysis
- Dboth version are subjected to an experiment simultaneously, the observations are recorded to determine which version is more successful
21Data adquisition & filtering
- Athis helps maintain data provenance throughout the big data analysis lifecycle, which helps establish and preserve data accuracy and quality
- Bmetadata is added through an automated mechanism to data received from both internal and external data sources
- Cany required purchase of tools, hardware, training, etc. need to be understood in advance, so that the anticipated investment can be weighed against the expected benefits of archieving the goals
- Dhelps decision-makers understand the business resources that will need to be utilized and which business challenges the analysis will tackle
22Data Extraction
- ASome of the data identified as input for the analysis may arrive in a format incompatible with the big data solution
- Bthe need to address disparate types of data is more likely with data from external sources
- Cmake it possible to develop highly reliable, highly available distributed big data solutions that can be deployed in a cluster
- DData needs to be imported before it can be processed by the big data solution
23Data Extraction
- Ais dedicated to extracting disparate data and transforming it into a format that the underlying big data solution can use for the purpose of the data analysis
- Bthe extend of extraction and transformation required depends on the types of analytics and capabilities of the big data solution
- Cprovenance can play an important role in determining the accuracy and quality of qustionable data
- Dis closely related to parallel data processing in how the same principle of "divide-and-conquer" is applied
24Data Extraction
- Aextracting text for text analytics, which requires scans of whole documents, will not be necessary if the underlying Big Data solution can already read the document in its native format directly
- Bfurther transformation is needed in order to separate the data into two separate fields as required by the big data solution
- Cit can also be used to make predictions about the values of the dependent variable while it is still unknown
- DHowever, ___________ is always archieved through physically separate machines that are networked together as a cluster
25Data Validation & Cleansing
- AInvalid data can skew and falsify analysis results
- BUnlike traditional enterprise data where the data structure is pre-defined and data is pre-validated, data input into big data analyses can be unstructured without any indication of validity
- CMore than one independent variable can be tested at the same time
- DThe _______ essencially acts a resource arbitrator that manages and allocates available resources
26Data Validation & Cleansing
- Aits complexity can further make it difficult to arrive at a set of suitable validation constraints
- Bis dedicated to establishing (often complex) validation rules and removing any known invalid data
- Cis closely related to the concept of classificatopm and clustering, although its algorithms focus on finding abnormal values
- Dfor batch analytics, ______________ can be achieved via an offline ETL operation
27Data Validation & Cleansing
- ABig data solutions often receive redundant data across different datasets
- Bthis redundancy can be exploited to explore interconnected datasets in order to assemble validation parameters and fill in missing valid data
- CA ___ represents a geographic measure by which different regions are color-coded according to a certain theme
- DA _________ is a file system that can store large files spread across a cluster
28Data Validation & Cleansing
- Afor batch analytics, ______________ can be achieved via an offline ETL operation
- BThe presence of invalid data is resulting in spikes. Although the data appears abnormal, it may be indicative of a new pattern
- CA _______ is generally expressed using a line chart, with time plotted on the x-axis and recorded data value plotted on the y-axis
- Dfor realtime analytics, a more complex in-memory system is required to validate and cleanse the data at the source
29Data Validation & Cleansing
- Aprovenance can play an important role in determining the accuracy and quality of qustionable data
- Bdata that appears to be invalid may still be valuable in that it may possess hidden patterns and trends
- CNo hypothesis or predetermined assumptions are generated
- DA _______ database is a non-relational database that is highly scalable, fault-tolerant and specifically designed to house unstructured data
30Data Aggregation & Representation
- AData may be spread across multiple datasets, requiring that datasets be joined together via common fields, in other cases, the same data fields may appear in multiple datasets
- BEither way, a method of data reconciliation is required or the dataset representing the correct value needs to be determined
- CLaw of Diminishing Marginal Utility
- DA ______ can be in the form of a chart or a map
31Data Aggregation & Representation
- Ais dedicated to integrating multiple datasets together to arrive at a unified view
- Bfuture dara analysis requirements need to be considered during this stage to help foster data reusability
- CThe ________ mechanism can also be used for support distributed locks, support distributed queues, establish a highly available registry for obtaining configuration information, reliable asynchronous communication between processes that are running on different servers
- Dessentially provides the ability to discover text rather than just search it
32Data structure and Semantics
- Aperforming the stage of data aggregation & representation can become complicated because of differences in this
- BReconciling these differences can require complex logic that is executed automatically without the need for human intervention
- CWithin Big Data ________ can first be applied to discover if a relationship exists
- Dboth version are subjected to an experiment simultaneously, the observations are recorded to determine which version is more successful
33Data structure
- AAlthough the data format may be the same, the data model may be different
- Bare an effective visual analysis technique for expressing patterns, data compositions via part-whole relations and geographic distributions of data
- CData Adquisition & Filtering
- DHadoop's batch-based data processing fully lends itself to the pay -per-use model of __________, which can reduce operational costs since a typical Hadoop cluster size can range from a few to a few thousand nodes
34Semantics
- AA value that is labelled differently in two different datasets may mean the same thing
- BInstead of hard-coding the required learning rules, either supervised or unsupervised machine learning is applied to develop the computer's understanding of the __________
- CNetwork Analysis
- DIn other areas such as the scientific domains, the objective may simply be to observe which version works better in order to improve a process or product
35Data Aggregation
- AThe large volumes processed by Big Data solutions can make____________ a time and effort-intensive operation
- BWhether _____________ is required or not, it is important to understand that the same data can be stored in many different forms. One form may be better suited for a particular type of analysis than another
- Crequire processing resources that they request from the resource manager
- Dthe data is then analyzed to prove or disprove the hypothesis and provide definitive answers to specific questions
36Data structure standarized
- Acan act as a common denominator that can be used for a range of analysis techniques and projects. This can require establishing a central, standard analysis repository, such as a NoSQL database
- BA big data _________ utilizes a distributed parallel programming framework that enables it to process very large amounts of data distributed across multiple nodes
- CThe _____ essencially acts a resource arbitrator that manages and allocates available resources
- Dcomprise random read/writes that involve fewer joins and require low-latency responses, with a smaller data footprint
37Data Analysis
- Ais dedicated to carrying out the actual analysis task, which typically involves one or more types of analysis
- Bthis stage can be iterative in nature, especially if the _________________ is exploratory so that analysis is repeated until the appropiate pattern or correlation is uncovered
- CA _______ may internally use a processing engine to process multiple large datasets in parallel
- Dthe accuracy and applicability of the patterns and relationships that are found in a large dataset will be higher than that of a smaller dataset
38Data Analysis
- Athe exploratory analysis approach is explained shortly, along with confirmatory analysis
- Bdepending on the type of analytics required, this stage can be as simple as querying a dataset to compute an aggregation for comparision
- Cmake it possible to develop highly reliable, highly available distributed big data solutions that can be deployed in a cluster
- DCorrelation, regression, time series analysis, classification, clustering, outlier detection, filtering, natural language processing, text analytics and sentiment analysis are considered forms of ________
39Data Analysis
- Ait can be as challenging as combining data mining and complex statistical analysis techniques to discover patterns and anomalies, or to generate a statistical or mathematical model to depict relationship between variables
- BThe approach taken when carrying out this stage can be classified as confirmatory analysis or exploratory analysis (the latter is linked to data mining)
- CThe results of completing the _______________ stage provide users with the ability to perform visual analysis, allowing for the discovery of answers to questions that users have not yet even formulated
- DA given ______ may support either data ingress or egress functions
40Confirmatory Data Analysis
- A_____________ is a deductive approach where the cause of phenomenon being investigated is proposed beforehand
- Bthe data is then analyzed to prove or disprove the hypothesis and provide definitive answers to specific questions
- Ccan be used to determine the number of entities that fall within a certain radius of another entity
- Dcan act as a common denominator that can be used for a range of analysis techniques and projects. This can require establishing a central, standard analysis repository, such as a NoSQL database
41hypothesis
- AThe proposed cause or assumption is called a ____________
- Bis an item filtering technique based on the collaboration (merging) of users' past behavior
- CThis type of environment is provided by a platform that is comprised of a set of distributed storage and processing technologies
- DAs the amount of digitized documents, e-mails, social media posts and log files increases, business have an increasing need to leverage any value that can be extracted from these forms of semi-structured and unstructured data
42Confirmatory Data Analysis
- Athe data is then analyzed to prove or disprove the hypothesis and provide definitive answers to specific questions
- BData samples are typically used
- Cthis information can then be integrated into the decision-making process
- DUnexpected findings or anomalies are usually ignored since a predetermined cause was assumed
43Exploratory Data Analysis
- A_____________ is an inductive approach that is closely associated to data mining
- BNo hypothesis or predetermined assumptions are generated
- Ccan be carried out via the use of supported by correlation, heat maps, time series analysis, network analysis, spatial data analysis, clustering, outlier detection, natural language processing and text analytics
- Dis an item filtering technique based on the collaboration (merging) of users' past behavior
44Exploratory Data Analysis
- AInstead, the data is explored through analysis to develop an understanding of the cause of the phenomenon
- BAlthough it may not provide definitive answers, this method provides a general direction that can facilitate the discovery of patterns or anomalies
- Crepresents a constant rate of change
- DLarge amounts of data and visual analysis are typically used
45Data visualization
- AThe ability to analyze massive amounts of data and find useful insights carries little value if the only ones that can interpret the results are the analysis
- Bis dedicated to using __________________ techniques and tools to graphically communicate the analysis results for efective interpretarion by business users
- Cis the process of finding data that is significantly different from or inconsistent with the rest of the data within a given dataset
- Dfor batch analytics, ______________ can be achieved via an offline ETL operation
46Data visualization
- ABusiness users need to be able to understand the results in order to obtain value from the analysis and subsequently have the ability to provide feedback
- BThe results of completing the _______________ stage provide users with the ability to perform visual analysis, allowing for the discovery of answers to questions that users have not yet even formulated
- CLarge amounts of data and visual analysis are typically used
- Dis an item filtering technique focused on the similarity between users and items
47Data visualization
- AThe same results may be presented in a number of different ways, which can influence the interpretation of the results
- BConsequently, it is important to use the most suitable visualization technique by keeping the business domain in context
- CAnother aspect to keep in mind is that providing a method of drilling down to comparatively simple statistics were generated
- DThe objective is to use graphic representations to develop a deeper understanding of the data being analyzed. Specifically, it helps identify and highlight hiden patterns, correlations and anomalies
48Analysis results
- ASubsequent to __________ being made available to business users to support business decision-making (such as via dashboard), there may be further oportunities to utilize the __________
- BNatural Language Processing
- CA ___________ provides the ability to design and process a complex sequence of operations that can be triggered either at set time intervals or when data becomes available
- Dincludes both text and speech recognition
49Utilization Analysis results
- Ais dedicated to determining how and where processed analysis data can be further leveraged
- BDepending on the nature of the analysis problems being addressed, it is possible for the analysis results to produce "models" that encapsulate new insights and understandings about the nature of the patterns and relationships that exist within the data that was just analyzed
- CData Transfer Engine
- Dis generally applied via the following two approaches: collaborative ____________ and content-based ____________
50Utilization Analysis results
- AA model look like a mathematical equation or a set of rules
- BModels can be used to improve business process logic, application system logic and can form the basis of a new system or software program
- CA distributed Big Data solution that needs to run on multiple servers relies on the coordination engine mechanism to ensure operational consistency across all of the participating servers
- Dnew models may be used to improve the programming logic within existing enterprise systems or may form the basis of new systems
51Input for enterprise systems
- AFiltering
- BAn ________ is employed when the comparatively simple data manipulation functions of a query engine are insufficient
- Cthe data analysis results may be automatically (or manually) fed directly into enterprise systems to enhance and optimized their behavior and performance
- Dnew models may be used to improve the programming logic within existing enterprise systems or may form the basis of new systems
52Business Process Optimization
- AThe identified patterns, correlations and anormalies discovered during the data analysis are used to refine business processes
- Bmodels may also lead to opportunities to improve business process logic
- Cis a computer's ability to comprehend human speech and text as naturally understood by humans
- DWhen two variables are considered to be _____________ they are considered to be aligned based on a linear relationship
53Alerts
- AData analysis results can be used as input for existing _______ or may form the basis of new _______
- Bthis helps maintain data provenance throughout the big data analysis lifecycle, which helps establish and preserve data accuracy and quality
- CText Analytics
- DRecommender systems may also be based on a hybrid of both collaborative _______ and content-based _______ to fine-tune the accuracy and effectiveness of generated suggestions
54Data Analysis Techniques
- AStatistical Analysis
- BVisual Analysis
- Cit can be as challenging as combining data mining and complex statistical analysis techniques to discover patterns and anomalies, or to generate a statistical or mathematical model to depict relationship between variables
- DNote that distributed file systems and databases are both on disk _________ mechanisms
55Data Analysis Techniques
- AMachine Learning
- BSemantic Analysis
- CA _______ database is a non-relational database that is highly scalable, fault-tolerant and specifically designed to house unstructured data
- DEach node in the _____ has its own dedicated resources such as memory and hard drive and runs its own operating system just like a desktop computer
56Statistical Analysis
- AA/B Testing
- BCorrelation
- CUnstructured text is generally much more difficult to analyze and search, compared to structured text
- DRegression
57Machine Learning
- AClassification
- BClustering
- CThe use of ________ can reduce development time and enables the manipulation of large datasets without the need to write complex programming logic
- Dit is vital that metadata be machine-readable and passed forward along subsequent analysis stages
58Machine Learning
- AOutlier Detection
- BFiltering
- CSome propietary ________ also provide specialized data analysis features, such as text analytics and machine log analysis processing
- DHadoop's batch-based data processing fully lends itself to the pay -per-use model of __________, which can reduce operational costs since a typical Hadoop cluster size can range from a few to a few thousand nodes
59Visual Analysis
- AHeat Maps
- BTime series analysis
- Cexamples of appenden metadata can include dataset size and structure, source information, date and time of creation or collection, language-specific information, etc.
- Dcan act as a common denominator that can be used for a range of analysis techniques and projects. This can require establishing a central, standard analysis repository, such as a NoSQL database
60Visual Analysis
- ANetwork Analysis
- BSpatial Data Analysis
- Cit can be based on either supervised or unsupervised learning
- DInvalid data can skew and falsify analysis results
61Semantic Analysis
- Asuggest that there is no relationship at all between the two variables
- BApplications of __________ include operations and logistic optimization, environmental sciences and infrastructure planning
- CNatural Language Processing
- DText Analytics
62Semantic Analysis
- ASentiment Analysis
- Bsuggest that there is no relationship at all between the two variables
- CApplications for ___________ include fraud detection, medical diagnosis, network data analysis and sensor data analysis
- DUnexpected findings or anomalies are usually ignored since a predetermined cause was assumed
63Statistical Analysis
- Auses statistical methods based on mathematical formulas as a means for analyzing data
- Bthis type of analysis is commonly used to describe datasets via summarization, such as providing the mean, median or mode of statistics associated with the dataset
- CSpatial or geospatial data is commonly used to identify the geographic location of individual entities
- DThe _____ essencially acts a resource arbitrator that manages and allocates available resources
64Statistical Analysis
- Ait can also be used to infer patterns and relationships within the dataset, such as regression and correlation
- Bis generally applied via the following two approaches: collaborative ____________ and content-based ____________
- Cis a supervised learning technique by which data is classified into relevant, previously learned categories
- DWe may be further interested in discovering how closely Variables A and B are related, which means we may also want to analyze the extend to which Variable B increases in relation to Variable A's increase
65A/B Testing
- Aalso known as split or bucket testing compares two versions of an element to determine which version is superior based on a pre-defined metric
- Bthe element can be a range of things
- Cis expressed as a decimal number between -1 to +1, which is known as the _____________ coefficient
- DClassification, outlier detection, filtering, natural language processing, text analytics and sentiment analysis can utilize ___________
66A/B Testing
- Athe current version of the element is called the control version, whereas the modified version is called the treatment
- Bboth version are subjected to an experiment simultaneously, the observations are recorded to determine which version is more successful
- CHowever, ___________ is always archieved through physically separate machines that are networked together as a cluster
- DInstead of hard-coding the required learning rules, either supervised or unsupervised machine learning is applied to develop the computer's understanding of the __________
67A/B Testing
- AAlthough __________ can be implemented in almost any domain, it is most often used in marketing
- BGenerally, the objective is to gauge human behavior with the goal of increasing sales
- CThis is a traditional data analysis principle that claims that data held in a reasonably sized dataset provides the maximum value
- DEither way, a method of data reconciliation is required or the dataset representing the correct value needs to be determined
68A/B Testing
- AIn other areas such as the scientific domains, the objective may simply be to observe which version works better in order to improve a process or product
- BA ______ can be in the form of a chart or a map
- Cfor batch analytics, ______________ can be achieved via an offline ETL operation
- DCorrelation, regression, time series analysis, classification, clustering, outlier detection, filtering, natural language processing, text analytics and sentiment analysis are considered forms of ________
69Correlation
- Ais an analysis technique used to determine whether two variables are related to each other
- Bif they are found to be related, the next step is to determine what their relationship is
- CQuery Engine
- DIn general, the more learning data the computer has, the more correctly it can decipher human text and speech
70Correlation
- AWe may be further interested in discovering how closely Variables A and B are related, which means we may also want to analyze the extend to which Variable B increases in relation to Variable A's increase
- BThe use of ________ helps to develop and understanding of a dataset and find relationships that can assist in explaining a phenomenon
- CNetwork Analysis
- DData may be spread across multiple datasets, requiring that datasets be joined together via common fields, in other cases, the same data fields may appear in multiple datasets
71Correlation
- AIs therefore commonly used for data mining where the identification of relationships between variables in a dataset leads to the discovery of patterns and anomalies
- BThis can reveal the nature of the dataset or the cause of a phenomenon
- CMigrating to the cloud is logical for enterprises planning to run analytics on datasets that are available via data markets, as most data markets store their data in the cloud such as Amazon S3
- DBig Data solutions require a distibuted processing environment that can accomodate large-scale data volumes, velocity and variety
72Correlated
- AWhen two variables are considered to be _____________ they are considered to be aligned based on a linear relationship
- BThis means that when one variable changes, the other variable also changes proportionally and constantly
- Citems can be ______ either based on a user's own behavior or by matching the behavior of multiple users
- DNote that a workflow engine may provide integration with a _______ to enable the automated import and export data
73Correlation
- Ais expressed as a decimal number between -1 to +1, which is known as the _____________ coefficient
- BThe degree of relationship changes from being strong to weak when moving from -1 to 0 or +1 to 0
- CFor example, a __________ can execute logic that collects relational data from multiple databases at regular intervals via the data transfer engine mechanism, applies a set of ETL operations via the processing engine mechanism and finally persists the results to a NoSQL storage device
- Dessentially provides the ability to discover text rather than just search it
74+1
- Asuggest that there is a strong positive relationship between the two variables
- BWhen one variable increases, the other also increases and viceversa
- Ctypically involve large quantities of data with sequential read/writes, and comprises a group of read or write queries
- DData Extraction
750
- Asuggest that there is no relationship at all between the two variables
- Bwhen one increases, the other may stay the same, or increase or decrease arbitrarily
- Cit can also be used to make predictions about the values of the dependent variable while it is still unknown
- DGenerally, the objective is to gauge human behavior with the goal of increasing sales
76-1
- Asuggest that there is a strong negative relationship between the two variables
- Bwhen one variable increases, the other decreases and viceversa
- Ccan be carried out via the use of supported by correlation, heat maps, time series analysis, network analysis, spatial data analysis, clustering, outlier detection, natural language processing and text analytics
- DTherefore, the value of each additional batch does not diminish value; rather, it provides more value
77Regression
- AThe analysis technique of _________ explores how a dependent variable is related to an independent variable within a dataset
- BAs a sample scenario, __________ could help determine the type of relationship that exists between temperature (independent variable) and crop yield (dependent variable)
- CIn the context of traditional data analysis, the ______ states that, starting with a reasonably large sample size, the value obtained from the analysis of additional data decreases as more data is successively added to the original sample
- DData Analysis
78Regression
- AApplying this technique helps determine how the value of the dependent variable changes in relation to change in the value of the independent variable
- BWhen the independent variable increases, for example, does the dependent variable also increase? If yes, is the increase in a linear or non-linear proportion?
- CBusiness Case Evaluation
- DA _________ comprises grouped read/writes, with a larger data footprint consisting of complex joins and high-latency responses
79Regression
- AMore than one independent variable can be tested at the same time
- BHowever, in such cases only one independent variable may change. The others are kept constant
- CThe results of completing the _______________ stage provide users with the ability to perform visual analysis, allowing for the discovery of answers to questions that users have not yet even formulated
- Da list of possible third-party data providers (data markets and publicity available datasets), are generally compiled. Some forms of external data may be embedded within blogs or other types of content-based Websites, in which case they may need to be harvested via automated tools
80Regression
- Acan help enable a better undestanding of what a phenomenon is, and why it occurred
- Bit can also be used to make predictions about the values of the dependent variable while it is still unknown
- CUsers of Big Data solutions can make numerous data processing requests, each of which can have different processing workload requirements
- DThe _____ essencially acts a resource arbitrator that manages and allocates available resources
81Linear regression
- Arepresents a constant rate of change
- Bit can be as challenging as combining data mining and complex statistical analysis techniques to discover patterns and anomalies, or to generate a statistical or mathematical model to depict relationship between variables
- Cthe ______ states that the confidence with which predictions can be made increases as the size of the data that is being analyzed increases
- DData samples are typically used
82Non-linear regression
- AThis type of environment is provided by a platform that is comprised of a set of distributed storage and processing technologies
- BHadoop's batch-based data processing fully lends itself to the pay -per-use model of __________, which can reduce operational costs since a typical Hadoop cluster size can range from a few to a few thousand nodes
- CA ________ is a method of storing and organizing data on a storage medium, such as hard drives, DVD´s, and flash drives
- Drepresents the variable rate of change
83Correlation
- Adoes not imply a causation. The change in the value of one variable may not be responsible for the change in the value of the second variable, although both may change at the same rate
- Bassumes that both variables are independent
- CWithin Big Data ________ can first be applied to discover if a relationship exists
- DHowever, ___________ is always archieved through physically separate machines that are networked together as a cluster
84Regression
- Adeal with already identified dependent and independent variables
- Bimplies that there is a degree of causation between the dependent and independent variables that may be direct or indirect
- Ccan then be applied to further explore the relationship and predict the values of the dependent variable, based on the known values of the independent variables
- Dis an example of the application of the law of large numbers
85Visual Analysis
- Ais a form of data analysis that involves the graphic representation of data to enable or enhance its visual perception
- Bbased on the premise that humans can understand and draw conclusions from graphics more quickly than from text, _______ act as a discovery tool in the field of Big Data
- CAs the amount of digitized documents, e-mails, social media posts and log files increases, business have an increasing need to leverage any value that can be extracted from these forms of semi-structured and unstructured data
- DIs therefore commonly used for data mining where the identification of relationships between variables in a dataset leads to the discovery of patterns and anomalies
86Visual Analysis
- AThe objective is to use graphic representations to develop a deeper understanding of the data being analyzed. Specifically, it helps identify and highlight hiden patterns, correlations and anomalies
- Bis also directly related to exploratory data analysis, as it encourages the formulation of questions from different angles
- CWorkflow Engine
- Drequire processing resources that they request from the resource manager
87Heat Maps
- Aare an effective visual analysis technique for expressing patterns, data compositions via part-whole relations and geographic distributions of data
- Bthey also facilitate the identification of areas of interest and the discovery of extreme (high/low) values within a dataset
- CMigrating to the cloud is logical for enterprises planning to run analytics on datasets that are available via data markets, as most data markets store their data in the cloud such as Amazon S3
- DData analysis results can be used as input for existing _______ or may form the basis of new _______
88Heat Maps
- AThe ______ itself is a visual, color-coded representation of data values
- BEach value is given a color according to its type, or the range that it falls under
- CSolely analyzing operational (structured) data may cause businesses to miss out on cost-saving or business expansion opportunities, especially those that are customer-focused
- DApplications of __________ include operations and logistic optimization, environmental sciences and infrastructure planning
89Heat Maps
- AA ______ can be in the form of a chart or a map
- BInstead of coloring the whole region, the map may be superimposed by a layer made up of collections of colored shapes representing various regions
- Csuggestions commonly pertain to recommending items, such as movies, books, web pages, people, etc.
- DSentiment Analysis
90chart
- AA _____ represents a matrix of values in which each cell is color-coded according to the value
- Bin order to qualify as a Big Data Problem, a business problem needs to be directly related to one or more of the Big Data characteristics of volume, velocity or variety
- Citems can be ______ either based on a user's own behavior or by matching the behavior of multiple users
- DBig data solutions often receive redundant data across different datasets
91map
- AA ___ represents a geographic measure by which different regions are color-coded according to a certain theme
- BAlthough __________ can be implemented in almost any domain, it is most often used in marketing
- CNLP, Text analytics and sentiment analysis be used in support of __________
- DAs a sample scenario, __________ could help determine the type of relationship that exists between temperature (independent variable) and crop yield (dependent variable)
92Heat Maps
- AInstead of coloring the whole region, the map may be superimposed by a layer made up of collections of colored shapes representing various regions
- BData needs to be imported before it can be processed by the big data solution
- CThe data collected for _______ is always time-dependent
- DNamed Entities(person, group, place, company), Pattern-Based Entities(social insurance number, zip code), Concepts (an abstract representation of a entity), Facts (relationship between entities)
93Time series Analysis
- Ais the analysis of data that is recorded over periodic intervals of time
- Bthis type of analysis makes use of _________, which is a time-ordered collections of values recorded over regular time intervals
- Cin order to qualify as a Big Data Problem, a business problem needs to be directly related to one or more of the Big Data characteristics of volume, velocity or variety
- Ddata that appears to be invalid may still be valuable in that it may possess hidden patterns and trends
94Time series Analysis
- Ahelps to uncover patterns within data that are time-dependent. Once identified, the pattern can be extrapolated for future predictions.
- Bare usually used for forecasting by identifying long-term trends, seasonal periodic patterns and irregular short-term variations in the dataset
- CFor example, a __________ can execute logic that collects relational data from multiple databases at regular intervals via the data transfer engine mechanism, applies a set of ETL operations via the processing engine mechanism and finally persists the results to a NoSQL storage device
- DBig Data solutions can be partially or fully deployed in clouds in order to leverage the storage and computing resources that are available from the cloud provider
95Time series Analysis
- AUnlike other types of analyses, _________ always includes time as a comparision variable
- BThe data collected for _______ is always time-dependent
- CData samples are typically used
- Dis solely based on the similarity between users' behavior, and requires a large amount of user behavior data in order to accurately filter items
96Time series Analysis
- AA _______ is generally expressed using a line chart, with time plotted on the x-axis and recorded data value plotted on the y-axis
- Bis the specialized analysis of text through the application of data mining, machine learning and natural language processing techniques to extract value out of unstructured text
- Cnew models may be used to improve the programming logic within existing enterprise systems or may form the basis of new systems
- Ddepending on the type of data source, data may come as a dump of files (such as data purchased from a third-party data provider), or may require API integration (such as with Twitter)
97Network
- AWithin the context of visual analysis, a _______ is a interconnected collection of entities
- Bnew models may be used to improve the programming logic within existing enterprise systems or may form the basis of new systems
- Cthis type of analysis makes use of _________, which is a time-ordered collections of values recorded over regular time intervals
- DConsequently, it is important to use the most suitable visualization technique by keeping the business domain in context
98Entity
- AAn ____ can be a person, a group or some other business domain object such as a product
- Bmay be connected with another directly or indirectly
- Cis a form of data analysis that involves the graphic representation of data to enable or enhance its visual perception
- DAlso known as online processing, ____________ processing follows an approach whereby data is processed interactively, without delay (resulting in low-latency responses)
99Network Analysis
- ASome connections may only be one-way, so that traversal in the reverse direction is not possible
- Bis a technique that focuses on analyzing relationships between entities within the network
- CFor example, a __________ can execute logic that collects relational data from multiple databases at regular intervals via the data transfer engine mechanism, applies a set of ETL operations via the processing engine mechanism and finally persists the results to a NoSQL storage device
- Dprovides analysis features more sophisticated than those of heat maps
100Network Analysis
- Ait involves plotting entities as nodes and connections as edges between nodes
- BThere are specialized variations of __________ include route optimization, social network analysis and spread prediction
- CUnlike other types of analyses, _________ always includes time as a comparision variable
- Dare based on predictive analytics techniques and therefore are associated with the same analysis techniques as predictive analytics. Additionally, _____ may utilize heat maps, network analysis and spatial data analysis to graphically show various outcomes
101Spatial Data Analysis
- Afocused on analyzing location-based data in order to find different geographic relationship and patterns between entities
- BSpatial or geospatial data is commonly used to identify the geographic location of individual entities
- Cin order to qualify as a Big Data Problem, a business problem needs to be directly related to one or more of the Big Data characteristics of volume, velocity or variety
- DThe ________ mechanism can also be used for support distributed locks, support distributed queues, establish a highly available registry for obtaining configuration information, reliable asynchronous communication between processes that are running on different servers
102Spatial Data Analysis
- Ais manipulated through a geographical information system (GIS) that plots spatial data on a map generally using its longitude and latitude coordinates
- BWith the ever-increasing availability of location-based data, _________ can be analyzed to gain location insights
- Cis dedicated to establishing (often complex) validation rules and removing any known invalid data
- DCorrelation
103Spatial Data Analysis
- AApplications of __________ include operations and logistic optimization, environmental sciences and infrastructure planning
- BData used as input for_________ can either contain exact locations (longitude,latitude) or the information required to calculate locations (such as zip codes or IP addresses)
- Cthe accuracy and applicability of the patterns and relationships that are found in a large dataset will be higher than that of a smaller dataset
- Dhelps decision-makers understand the business resources that will need to be utilized and which business challenges the analysis will tackle
104Spatial Data Analysis
- Aprovides analysis features more sophisticated than those of heat maps
- Bcan be used to determine the number of entities that fall within a certain radius of another entity
- Cthe need to address disparate types of data is more likely with data from external sources
- Dis dedicated to establishing (often complex) validation rules and removing any known invalid data
105Machine Learning
- ALaw of large numbers
- BLaw of Diminishing Marginal Utility
- CA target user´s past behavior (likes, rating, purchase history, etc.) is collaborated with the behavior of similar users
- Dinitial iteration of the big data analysis lifecycle will require more up-front investment of Big Data technologies, products and training compared to later iterations where these earlier investment can be repeatedly leveraged
106Law of large numbers
- Athe ______ states that the confidence with which predictions can be made increases as the size of the data that is being analyzed increases
- Bthe accuracy and applicability of the patterns and relationships that are found in a large dataset will be higher than that of a smaller dataset
- CData Extraction
- Dis an analysis technique used to determine whether two variables are related to each other
107Law of large numbers
- Athis means that the greater the amount of data available for analysis, the better we become at making correct decisions
- BWithin computing, a ______ is a tightly coupled collection of servers, or nodes. These servers usually have the same hardware specifications and are connected together via network to work as a single unit
- CUnlike traditional enterprise data where the data structure is pre-defined and data is pre-validated, data input into big data analyses can be unstructured without any indication of validity
- DClassification
108Law of Diminishing Marginal Utility
- AIn the context of traditional data analysis, the ______ states that, starting with a reasonably large sample size, the value obtained from the analysis of additional data decreases as more data is successively added to the original sample
- BThis is a traditional data analysis principle that claims that data held in a reasonably sized dataset provides the maximum value
- CA _______ provides a logical view of the data stored on the storage medium as a tree structure of files and directories
- Dthis redundancy can be exploited to explore interconnected datasets in order to assemble validation parameters and fill in missing valid data
109Law of Diminishing Marginal Utility
- AThe ____ does not apply to Big Data
- BThe greater the volume and variety of data that Big Data solutions can process allows for each additional batch of data to carry greater potential of unearthing new patterns and anomalies
- Cfor speech recognition, the system attemps to comprehend the speech and then performs an action, such as transcribing text
- DApplying this technique helps determine how the value of the dependent variable changes in relation to change in the value of the independent variable
110Law of Diminishing Marginal Utility
- ATherefore, the value of each additional batch does not diminish value; rather, it provides more value
- BClassification
- CThis means that when one variable changes, the other variable also changes proportionally and constantly
- Dis an example of the application of the law of large numbers
111Classification
- Ais a supervised learning technique by which data is classified into relevant, previously learned categories
- Bthe system is fed data that is already categorized or labeled, so that it can develop an understanding of the different categories
- Ctherefore, it is advisable to store a verbatim copy of the original dataset before proceeding with the filtering. To save on required storage space, the verbatim copy is compressed before storage
- DTherefore, the value of each additional batch does not diminish value; rather, it provides more value
112Classification
- Athe system is fed unknown (but similar) data for classification, based on the understanding it developed
- Ba common application of this technique is for the filtering of e-mail spam. Note that ___________ can be performed for two or more categories
- Ccan help enable a better undestanding of what a phenomenon is, and why it occurred
- Dit involves plotting entities as nodes and connections as edges between nodes
113Classification
- Ain a simplified _____ process, the machine is fed labeled data during training that builds its understanding of the _______. The machine is then fed unlabeled data, which is classifies itself
- Balso known as split or bucket testing compares two versions of an element to determine which version is superior based on a pre-defined metric
- CA file is an atomic unit of storage used by the _________ to stored data. Files are organizated inside of a directory
- DThe objective is to use graphic representations to develop a deeper understanding of the data being analyzed. Specifically, it helps identify and highlight hiden patterns, correlations and anomalies
114Clustering
- Ais an unsupervised learning technique by which data is divided into different groups so that the data in each group has similar properties
- BThere is no prior learning of categories required; intead, categories are implicity generated based on the data groupings
- CBig Data solutions can be partially or fully deployed in clouds in order to leverage the storage and computing resources that are available from the cloud provider
- DApplications include document classification and search, as well as builiding a 360-degree view of a customer by extracting information from a CRM system
115Clustering
- AHow the data is grouped depends on the type of algorithm used. Each algorithm uses a different technique to identify ______
- Bis generally used in data mining to get an understanding of the properties of a given dataset. After developing this understanding, classification can be used to make better predictions about similar, but new or unseen data
- CIs solely dedicated to individual user preferences and does not require data about other users
- DA ______ can be in the form of a chart or a map
116Clustering
- Acan be applied to the categorization of unknown documents, and to personalized marketing campaings by grouping together customers with similar behavior
- BWithin computing, a ______ is a tightly coupled collection of servers, or nodes. These servers usually have the same hardware specifications and are connected together via network to work as a single unit
- Citems can be ______ either based on a user's own behavior or by matching the behavior of multiple users
- Dthe ______ states that the confidence with which predictions can be made increases as the size of the data that is being analyzed increases
117Outlier Detection
- Ais the process of finding data that is significantly different from or inconsistent with the rest of the data within a given dataset
- BThe machine learning technique is used to identify anomalies, abnormalities and desviation that can be advantageous (such as oportunities) or disadvantageous (such a risk)
- CThe data collected for _______ is always time-dependent
- Dfor realtime analytics, a more complex in-memory system is required to validate and cleanse the data at the source
118Outlier Detection
- Ais closely related to the concept of classificatopm and clustering, although its algorithms focus on finding abnormal values
- Bit can be based on either supervised or unsupervised learning
- Cinvolves the simultaneous execution of multiple sub-tasks that collectivelly comprise a larger task
- Dit can also be used to infer patterns and relationships within the dataset, such as regression and correlation
119Outlier Detection
- AApplications for ___________ include fraud detection, medical diagnosis, network data analysis and sensor data analysis
- Bsuggest that there is a strong positive relationship between the two variables
- CTo the client, a file appears local and can be accessed via multiple locations
- DHeat Maps
120Filtering
- Ais the automated process of finding relevant items from a pool of items
- Bitems can be ______ either based on a user's own behavior or by matching the behavior of multiple users
- CThe ____ does not apply to Big Data
- DAlthough __________ can be implemented in almost any domain, it is most often used in marketing
121Filtering
- Ais generally applied via the following two approaches: collaborative ____________ and content-based ____________
- BA common medium by which ________ is implemented is via the use of a recommender system
- CA given ______ may support either data ingress or egress functions
- DA ________ generally provides only one of the listed functions
122Colaborative Filtering
- Ais an item filtering technique based on the collaboration (merging) of users' past behavior
- BA target user´s past behavior (likes, rating, purchase history, etc.) is collaborated with the behavior of similar users
- CWe may be further interested in discovering how closely Variables A and B are related, which means we may also want to analyze the extend to which Variable B increases in relation to Variable A's increase
- DThere are specialized variations of __________ include route optimization, social network analysis and spread prediction
123Colaborative Filtering
- ABased on the similarity of the user´s behavior, items are filtered for the target user
- Bis solely based on the similarity between users' behavior, and requires a large amount of user behavior data in order to accurately filter items
- CA _____ represents a matrix of values in which each cell is color-coded according to the value
- DThe presence of invalid data is resulting in spikes. Although the data appears abnormal, it may be indicative of a new pattern
124Colaborative Filtering
- Ais an example of the application of the law of large numbers
- BA ______ can be in the form of a chart or a map
- Cthe system is fed unknown (but similar) data for classification, based on the understanding it developed
- D_____________ is an inductive approach that is closely associated to data mining
125Content-based Filtering
- Ais an item filtering technique focused on the similarity between users and items
- BA user profile is created based on the user´s past behavior (likes, rating, purchase history, etc.)
- CAnalytics Engine
- Dcan be used to determine the number of entities that fall within a certain radius of another entity
126Content-based Filtering
- AThe similarities identified between the user profile and the attributes of various items, lead to items being filtered for the user
- BIs solely dedicated to individual user preferences and does not require data about other users
- CApplying this technique helps determine how the value of the dependent variable changes in relation to change in the value of the independent variable
- DHowever, in such cases only one independent variable may change. The others are kept constant
127Filtering
- AA recommender system predicts user preferences and generate suggestions for the user accordingly
- Bsuggestions commonly pertain to recommending items, such as movies, books, web pages, people, etc.
- Crepresents a constant rate of change
- Dcan be carried out via the use of supported by correlation, heat maps, time series analysis, network analysis, spatial data analysis, clustering, outlier detection, natural language processing and text analytics
128Filtering
- AA recommender system typically uses either colaborative _____ or content-based _________ to generate suggestions
- BRecommender systems may also be based on a hybrid of both collaborative _______ and content-based _______ to fine-tune the accuracy and effectiveness of generated suggestions
- CClassification, outlier detection, filtering, natural language processing, text analytics and sentiment analysis can utilize ___________
- DData analysis results can be used as input for existing _______ or may form the basis of new _______
129Semantic Analysis
- AIn order for the machines to extract valuable information, text and speech data needs to be understood by the machines in the same way as humans do. _____ represents practices for extracting meaningful information from textual and speech data
- Brequire processing resources that they request from the resource manager
- CThe same results may be presented in a number of different ways, which can influence the interpretation of the results
- DInstead, the data is explored through analysis to develop an understanding of the cause of the phenomenon
130Natural Language Processing
- Ais a computer's ability to comprehend human speech and text as naturally understood by humans
- Bthis allows computers to perform a variety of useful task, such as full-text searches
- CA _______ database generally provides an API-based query interface, rather than the SQL Interface
- DEach node in the _____ has its own dedicated resources such as memory and hard drive and runs its own operating system just like a desktop computer
131Natural Language Processing
- AInstead of hard-coding the required learning rules, either supervised or unsupervised machine learning is applied to develop the computer's understanding of the __________
- BIn general, the more learning data the computer has, the more correctly it can decipher human text and speech
- CA distributed Big Data solution that needs to run on multiple servers relies on the coordination engine mechanism to ensure operational consistency across all of the participating servers
- Dfunctionally can be further grouped into the following categories: event, file, relational
132Natural Language Processing
- Aincludes both text and speech recognition
- Bfor speech recognition, the system attemps to comprehend the speech and then performs an action, such as transcribing text
- CA user profile is created based on the user´s past behavior (likes, rating, purchase history, etc.)
- DThe processing engine enables data to be queried and manipulated in other ways, but to implement this type of functionality requires custom programming
133Text Analytics
- AUnstructured text is generally much more difficult to analyze and search, compared to structured text
- Bis the specialized analysis of text through the application of data mining, machine learning and natural language processing techniques to extract value out of unstructured text
- CAs the amount of digitized documents, e-mails, social media posts and log files increases, business have an increasing need to leverage any value that can be extracted from these forms of semi-structured and unstructured data
- DUseful insights from text-based data can be gained by helping businesses develop an understanding of the information that is contained within a large body of text
134Text Analytics
- Aessentially provides the ability to discover text rather than just search it
- BThe basic tenet of ___________ is to turn unstructured text into data that can be searched and analyzed
- CAnalysts working with big data solutions are not expected to know how to program processing engines
- Dcomprise random read/writes that involve fewer joins and require low-latency responses, with a smaller data footprint
135Text Analytics
- ASolely analyzing operational (structured) data may cause businesses to miss out on cost-saving or business expansion opportunities, especially those that are customer-focused
- BApplications include document classification and search, as well as builiding a 360-degree view of a customer by extracting information from a CRM system
- CHowever, in such cases only one independent variable may change. The others are kept constant
- Dis a form of data analysis that involves the graphic representation of data to enable or enhance its visual perception
136Text Analytics
- Agenerally involves two steps: Parsing text within documents to extract, Categorization of documents using these extracted entities and facts
- Bthe extracted information can be used to perform a context-specific search on entities, based on the type of relationship that exists between the entities
- Cidentifying a wider variety of data sources may increase the probability of finding hidden patterns and correlations
- DSimilarly, processed data may need to be exported to other systems before it can be used outside of the big data solution
137Parsing text within documents to extract:
- ANamed Entities(person, group, place, company), Pattern-Based Entities(social insurance number, zip code), Concepts (an abstract representation of a entity), Facts (relationship between entities)
- BData Extraction
- Cis generally used in data mining to get an understanding of the properties of a given dataset. After developing this understanding, classification can be used to make better predictions about similar, but new or unseen data
- DThe ________ mechanisms is responsible for processing data (usually retrieved from storage devices) based on pre-defined logic, in order to produce a result
138Sentiment Analysis
- Ais a specialized form of text analysis that focuses on determining the bias or emotions of individuals
- Bthis form of analysis determines the attitude of the author (of the text) by analyzing the text within the context of the natural language
- CThe proposed cause or assumption is called a ____________
- DIn other areas such as the scientific domains, the objective may simply be to observe which version works better in order to improve a process or product
139Sentiment Analysis
- Anot only provides information about how individuals feel, but also the intensity of their feeling
- Bthis information can then be integrated into the decision-making process
- CMachine Learning
- DInstead, the data is explored through analysis to develop an understanding of the cause of the phenomenon
140Sentiment Analysis
- ACommon applications for __________ include early identification of customer satisfaction or dissatisfaction, gauging product sucess or failure and spotting new trends
- BUtilization of Analysis Results
- CGenerally, the objective is to gauge human behavior with the goal of increasing sales
- Dare usually divided into two types: Batch and Transactional
141Quantitative Analysis
- ACorrelation and regression are examples of ________. A/B testing can make use of ____________ techniques for results comparision.
- BUnstructured text is generally much more difficult to analyze and search, compared to structured text
- CStorage Device
- DClustering
142Qualitative Analysis
- ANLP, Text analytics and sentiment analysis be used in support of __________
- BMachine Learning
- CTo the client, a file appears local and can be accessed via multiple locations
- DFor example, a __________ can execute logic that collects relational data from multiple databases at regular intervals via the data transfer engine mechanism, applies a set of ETL operations via the processing engine mechanism and finally persists the results to a NoSQL storage device
143Data Mining
- Acan be carried out via the use of supported by correlation, heat maps, time series analysis, network analysis, spatial data analysis, clustering, outlier detection, natural language processing and text analytics
- Bthis stage can be iterative in nature, especially if the _________________ is exploratory so that analysis is repeated until the appropiate pattern or correlation is uncovered
- CAn ________ is employed when the comparatively simple data manipulation functions of a query engine are insufficient
- Dmetadata is added through an automated mechanism to data received from both internal and external data sources
144Descriptive Analytics
- AA/B testing, heat maps and spatial data analysis are considered forms of ____________
- BThere are specialized variations of __________ include route optimization, social network analysis and spread prediction
- CThe output of one workflow can become the input of another workflow
- DStrategic BI and analytics fall in this category, since they are highly read intensive task involving large volumes of data
145Diagnostic Analytics
- ACorrelation, regression, time series analysis, network analysis and spatial data analysis are considered forms of _________
- BThe workflow logic processed by a _____________ mechanism can involve the participation of other big data mechanism
- CThe ________ mechanisms is responsible for processing data (usually retrieved from storage devices) based on pre-defined logic, in order to produce a result
- Din order to qualify as a Big Data Problem, a business problem needs to be directly related to one or more of the Big Data characteristics of volume, velocity or variety
146Predictive Analysis
- ACorrelation, regression, time series analysis, classification, clustering, outlier detection, filtering, natural language processing, text analytics and sentiment analysis are considered forms of ________
- Bis an unsupervised learning technique by which data is divided into different groups so that the data in each group has similar properties
- CNamed Entities(person, group, place, company), Pattern-Based Entities(social insurance number, zip code), Concepts (an abstract representation of a entity), Facts (relationship between entities)
- Dprovenance can play an important role in determining the accuracy and quality of qustionable data
147Prescriptive Analytics
- Aare based on predictive analytics techniques and therefore are associated with the same analysis techniques as predictive analytics. Additionally, _____ may utilize heat maps, network analysis and spatial data analysis to graphically show various outcomes
- BApplying this technique helps determine how the value of the dependent variable changes in relation to change in the value of the independent variable
- CThis can reveal the nature of the dataset or the cause of a phenomenon
- DTime series analysis
148Supervised Learning
- AClassification, outlier detection, filtering, natural language processing, text analytics and sentiment analysis can utilize ___________
- BA big data _________ utilizes a distributed parallel programming framework that enables it to process very large amounts of data distributed across multiple nodes
- Cuses statistical methods based on mathematical formulas as a means for analyzing data
- DA user profile is created based on the user´s past behavior (likes, rating, purchase history, etc.)
149Unsupervised Learning
- AClustering, outlier detection, filtering, natural language processing, text analytics and sentiment analysis can utilize ___________
- BData analysis results can be used as input for existing _______ or may form the basis of new _______
- CA _____ represents a matrix of values in which each cell is color-coded according to the value
- DModels can be used to improve business process logic, application system logic and can form the basis of a new system or software program
150Cluster
- AWithin computing, a ______ is a tightly coupled collection of servers, or nodes. These servers usually have the same hardware specifications and are connected together via network to work as a single unit
- BEach node in the _____ has its own dedicated resources such as memory and hard drive and runs its own operating system just like a desktop computer
- CThese engines may provide the agent-based processing of inflight data, which enables various data cleasing and transformation activities to be performed in realtime
- DUnexpected findings or anomalies are usually ignored since a predetermined cause was assumed
151Cluster
- AIn the diagram, a _____ is used to execute a task based on distributed / parallel data processing frameworks
- BA/B Testing
- CBig Data solutions require a distibuted processing environment that can accomodate large-scale data volumes, velocity and variety
- DMigrating to the cloud is logical for enterprises planning to run analytics on datasets that are available via data markets, as most data markets store their data in the cloud such as Amazon S3
152File System
- AA ________ is a method of storing and organizing data on a storage medium, such as hard drives, DVD´s, and flash drives
- BA file is an atomic unit of storage used by the _________ to stored data. Files are organizated inside of a directory
- CThis can reveal the nature of the dataset or the cause of a phenomenon
- DThe proposed cause or assumption is called a ____________
153File System
- AA _______ provides a logical view of the data stored on the storage medium as a tree structure of files and directories
- BOperating systems employ ______ for data storage. Each operating system provides support for one or more ________, like NTFS for windows and ext for linux
- Cthis form of analysis determines the attitude of the author (of the text) by analyzing the text within the context of the natural language
- DWithin Big Data ________ can first be applied to discover if a relationship exists
154Distributed File System
- AA _________ is a file system that can store large files spread across a cluster
- BTo the client, a file appears local and can be accessed via multiple locations
- Cis the process of finding data that is significantly different from or inconsistent with the rest of the data within a given dataset
- DNatural Language Processing
155Distributed File System
- AExamples include the Google File System and Hadoop ________
- Brequires that a business case be created, assessed and approved prior to proceeding with the actual hands-on analysis task
- CMachine Learning
- DData Aggregation & Representation
156NoSQL
- AA _______ database is a non-relational database that is highly scalable, fault-tolerant and specifically designed to house unstructured data
- BA _______ database generally provides an API-based query interface, rather than the SQL Interface
- CThe use of ________ helps to develop and understanding of a dataset and find relationships that can assist in explaining a phenomenon
- Dwhen one increases, the other may stay the same, or increase or decrease arbitrarily
157NoSQL
- AHowever, some _______ databases may also provide a SQL-like query interface
- Bthis allows computers to perform a variety of useful task, such as full-text searches
- Cdepending on the type of analytics required, this stage can be as simple as querying a dataset to compute an aggregation for comparision
- Dprocessing engine, storage device, resource manager
158Parallel Data Processing
- Ainvolves the simultaneous execution of multiple sub-tasks that collectivelly comprise a larger task
- Bthe premise is to reduce the execution time by dividing a single larger task into multiple smaller task
- CA _________ in Big Data os defined as the amount and nature of data that is processed within a certain amount of time
- DFor example, a __________ can execute logic that collects relational data from multiple databases at regular intervals via the data transfer engine mechanism, applies a set of ETL operations via the processing engine mechanism and finally persists the results to a NoSQL storage device
159Parallel Data Processing
- AAlthough __________ can be archieved through multiple networked machines, it is more typically achieved within the confines of a single machine (multiple processors or cores)
- Bthe system is fed data that is already categorized or labeled, so that it can develop an understanding of the different categories
- CLaw of Diminishing Marginal Utility
- Dprovides analysis features more sophisticated than those of heat maps
160Distributed Data Processing
- Ais closely related to parallel data processing in how the same principle of "divide-and-conquer" is applied
- BHowever, ___________ is always archieved through physically separate machines that are networked together as a cluster
- Cessentially provides the ability to discover text rather than just search it
- DThis allows large amounts of data to be imported or exported within a short period of time
161Processing workloads
- AA _________ in Big Data os defined as the amount and nature of data that is processed within a certain amount of time
- Bare usually divided into two types: Batch and Transactional
- Cincludes both text and speech recognition
- DA distributed Big Data solution that needs to run on multiple servers relies on the coordination engine mechanism to ensure operational consistency across all of the participating servers
162Batch Workload
- AAlso known as offline processing, ________ processing involves processing data in batches and usually imposes delays (resulting in high-latency responses)
- Btypically involve large quantities of data with sequential read/writes, and comprises a group of read or write queries
- Calso known as split or bucket testing compares two versions of an element to determine which version is superior based on a pre-defined metric
- DAn ____ can be a person, a group or some other business domain object such as a product
163Batch Workload
- AQueries can be complex and involve multiple joins
- BStrategic BI and analytics fall in this category, since they are highly read intensive task involving large volumes of data
- CSentiment Analysis
- DNLP, Text analytics and sentiment analysis be used in support of __________
164Batch Workload
- AA _________ comprises grouped read/writes, with a larger data footprint consisting of complex joins and high-latency responses
- BSpatial Data Analysis
- CCorrelation, regression, time series analysis, network analysis and spatial data analysis are considered forms of _________
- DUsers of Big Data solutions can make numerous data processing requests, each of which can have different processing workload requirements
165Transactional workload
- AAlso known as online processing, ____________ processing follows an approach whereby data is processed interactively, without delay (resulting in low-latency responses)
- Binvolves small amounts of data with random read/writes
- CData Validation & Cleansing
- DA/B Testing
166Transactional workload
- AOLTP and operational systems (write-intensive) as well as operational BI and analytics (read-intensive), both fall within this category
- BAlthough these workloads contain a mix of read/write queries, they are generally more write-intensive than read-intensive
- Ccan act as a common denominator that can be used for a range of analysis techniques and projects. This can require establishing a central, standard analysis repository, such as a NoSQL database
- Dcomprise random read/writes that involve fewer joins and require low-latency responses, with a smaller data footprint
167Cloud Computing
- Ais a specialized form of distibuted computing that introduce utilization models for remotely provisioning scalable and measured IT resources
- BBig Data solutions can be partially or fully deployed in clouds in order to leverage the storage and computing resources that are available from the cloud provider
- CData samples are typically used
- DIt can also represent hierarchical values by using color-coded nested rectangles
168Cloud Computing
- Athe clustered processing resources required by Big Data solutions can benefit from the highly scalable and elastic IT resources available on cloud-based environments
- BHadoop's batch-based data processing fully lends itself to the pay -per-use model of __________, which can reduce operational costs since a typical Hadoop cluster size can range from a few to a few thousand nodes
- Cis generally applied via the following two approaches: collaborative ____________ and content-based ____________
- DIn short _______ provides the three ingredients required for a big data solutions: input data, computing and storage
169It makes sence from enterprises already using cloud computing to reuse the cloud from their Big Data initiatives, because:
- AIT already possesses the required cloud computing skills
- Bthe imput data already exists in the cloud
- CCorrelation, regression, time series analysis, network analysis and spatial data analysis are considered forms of _________
- DIn the context of traditional data analysis, the ______ states that, starting with a reasonably large sample size, the value obtained from the analysis of additional data decreases as more data is successively added to the original sample
170Cloud Computing
- AMigrating to the cloud is logical for enterprises planning to run analytics on datasets that are available via data markets, as most data markets store their data in the cloud such as Amazon S3
- BWorkflow Engine
- Cnot only provides information about how individuals feel, but also the intensity of their feeling
- DThis can reveal the nature of the dataset or the cause of a phenomenon
171Big data Mechanisms
- ABig Data solutions require a distibuted processing environment that can accomodate large-scale data volumes, velocity and variety
- BThis type of environment is provided by a platform that is comprised of a set of distributed storage and processing technologies
- Cit can be beneficial to identify as many types of related data sources and insights as possible, especially when we dont know exactly what we're looking for
- DIs solely dedicated to individual user preferences and does not require data about other users
172Big data Mechanisms
- Arepresents the primary, common components of big data solutions, regardless of the open source or vendor products used for implementation
- BStorage Device
- CInstead of coloring the whole region, the map may be superimposed by a layer made up of collections of colored shapes representing various regions
- DQuery Engine
173Big data Mechanisms
- AProcessing Engine
- BResource Manager
- CApplications of __________ include operations and logistic optimization, environmental sciences and infrastructure planning
- Dis generally used in data mining to get an understanding of the properties of a given dataset. After developing this understanding, classification can be used to make better predictions about similar, but new or unseen data
174Big data Mechanisms
- AData Transfer Engine
- BAnalytics Engine
- Cis closely related to parallel data processing in how the same principle of "divide-and-conquer" is applied
- DThe data collected for _______ is always time-dependent
175Big data Mechanisms
- AWorkflow Engine
- BCoordination Engine
- CRecommender systems may also be based on a hybrid of both collaborative _______ and content-based _______ to fine-tune the accuracy and effectiveness of generated suggestions
- DThere is no prior learning of categories required; intead, categories are implicity generated based on the data groupings
176At minimun, any given big data solution needs to contain the _____, ______ and _______ mechanism in order to effectively process large datasets in support of the big data analysis lifecycle
- Aprocessing engine, storage device, resource manager
- Bstorage device, analytics engine, coordination engine
- Cprocessing engine , query engine, data transfer engine
- Dresource manager, analytics engine, workflow engine
177Storage Device
- A___________ mechanisms provide the underlying data storage environment for persisting the datasets that are processed by big data solutions
- BA ________ is a method of storing and organizing data on a storage medium, such as hard drives, DVD´s, and flash drives
- CA _______ can exists as a distibuted file system or a database
- DThe ability to analyze massive amounts of data and find useful insights carries little value if the only ones that can interpret the results are the analysis
178Storage Device
- ADistributed file systems can be used for persisting immutable data that is intended for streaming access or batch processing
- BDatabases, such as NoSQL repositories, can be used for structured and unstructured storage and read/write data access
- CNote that distributed file systems and databases are both on disk _________ mechanisms
- DNatural Language Processing
179Processing Engine
- AThe ________ mechanisms is responsible for processing data (usually retrieved from storage devices) based on pre-defined logic, in order to produce a result
- BAny data processing that is requested by the big data solution is fulfilled by the __________
- CWhether _____________ is required or not, it is important to understand that the same data can be stored in many different forms. One form may be better suited for a particular type of analysis than another
- DHadoop's batch-based data processing fully lends itself to the pay -per-use model of __________, which can reduce operational costs since a typical Hadoop cluster size can range from a few to a few thousand nodes
180Processing Engine
- AA big data _________ utilizes a distributed parallel programming framework that enables it to process very large amounts of data distributed across multiple nodes
- Brequire processing resources that they request from the resource manager
- CClassification
- Dare usually used for forecasting by identifying long-term trends, seasonal periodic patterns and irregular short-term variations in the dataset
181Batch Processing Engine
- AProvides support for batch data where processing tasks can take anywhere from minutes to hours to complete. This type of processing engine is considered to have high latency
- BThe identified patterns, correlations and anormalies discovered during the data analysis are used to refine business processes
- CWhen one variable increases, the other also increases and viceversa
- DOperating systems employ ______ for data storage. Each operating system provides support for one or more ________, like NTFS for windows and ext for linux
182Realtime Processing Engine
- AProvides support for realtime data with sub-seconds response times. This type of processing engine is considered to have low latency
- BTo the client, a file appears local and can be accessed via multiple locations
- CMigrating to the cloud is logical for enterprises planning to run analytics on datasets that are available via data markets, as most data markets store their data in the cloud such as Amazon S3
- Ddepending on the type of data source, data may come as a dump of files (such as data purchased from a third-party data provider), or may require API integration (such as with Twitter)
183Resource Manager
- AUsers of Big Data solutions can make numerous data processing requests, each of which can have different processing workload requirements
- BData that is held in storage can be processed in a variety of ways by a given Big Data solutions and all data processing requests require the allocation of processing resources
- Cit involves plotting entities as nodes and connections as edges between nodes
- Dthe system is fed data that is already categorized or labeled, so that it can develop an understanding of the different categories
184Resource Manager
- AA _______ acts as a schedules and prioritizes processing requests according to individual processing workload requirements
- BThe _____ essencially acts a resource arbitrator that manages and allocates available resources
- CA value that is labelled differently in two different datasets may mean the same thing
- DThe proposed cause or assumption is called a ____________
185Data Transfer Engine
- AData needs to be imported before it can be processed by the big data solution
- BSimilarly, processed data may need to be exported to other systems before it can be used outside of the big data solution
- Cthis form of analysis determines the attitude of the author (of the text) by analyzing the text within the context of the natural language
- DText Analytics
186Data Transfer Engine
- AA ________ engine enables data to be moved in or out big data solution storage devices
- BUnlike other data processing systems where input data conforms to a schema and is mostly structured, data sources for a big data solution tend to include a mix of structured and unstructured data
- Cis dedicated to determining how and where processed analysis data can be further leveraged
- DA given ______ may support either data ingress or egress functions
187Data Transfer ingress and egress
- Afunctionally can be further grouped into the following categories: event, file, relational
- Bthe processing engine mechanism will often use the ___________ to coordinate data processing across a large number of servers. This way, the processing engine does not require its own coordination logic
- Ccan help enable a better undestanding of what a phenomenon is, and why it occurred
- Dtherefore, it is advisable to store a verbatim copy of the original dataset before proceeding with the filtering. To save on required storage space, the verbatim copy is compressed before storage
188Data Transfer Engine
- AA ________ generally provides only one of the listed functions
- BIt is common for multiple diferent ________ to be part a big data solution to facilitate a range of import and export requirements for different types of data
- CA _______ provides a logical view of the data stored on the storage medium as a tree structure of files and directories
- Dare based on predictive analytics techniques and therefore are associated with the same analysis techniques as predictive analytics. Additionally, _____ may utilize heat maps, network analysis and spatial data analysis to graphically show various outcomes
189Data Transfer Ingress Engine
- AEvent-based __________ generally use a publish-subcribe model based on the use of a queue to ensure high reliability and availability
- BA file is an atomic unit of storage used by the _________ to stored data. Files are organizated inside of a directory
- Cit can be based on either supervised or unsupervised learning
- DThe data collected for _______ is always time-dependent
190Data Transfer Engine
- AThese engines may provide the agent-based processing of inflight data, which enables various data cleasing and transformation activities to be performed in realtime
- Benable the substitution of data that is distributed across a range of sources residing in multiple systems outside of the big data solution
- CHeat Maps
- Dis manipulated through a geographical information system (GIS) that plots spatial data on a map generally using its longitude and latitude coordinates
191Data Transfer Engine
- AA _______ may internally use a processing engine to process multiple large datasets in parallel
- BThis allows large amounts of data to be imported or exported within a short period of time
- CNote that a workflow engine may provide integration with a _______ to enable the automated import and export data
- Dis a computer's ability to comprehend human speech and text as naturally understood by humans
192Query Engine
- AThe processing engine enables data to be queried and manipulated in other ways, but to implement this type of functionality requires custom programming
- BAnalysts working with big data solutions are not expected to know how to program processing engines
- Cthis form of analysis determines the attitude of the author (of the text) by analyzing the text within the context of the natural language
- Dthe extracted information can be used to perform a context-specific search on entities, based on the type of relationship that exists between the entities
193Query Engine
- AThe _______ mechanism abstracts the processing engine from end-users by providing a front-end user-interface that can used to query underlying data, along with features for creating query execution plans
- BLanguages that are more familiar and easier to work with (such as SQL) can be used by non-technical users to perform ETL tasks and run ad hoc queries for data analysis activities
- Cthis helps maintain data provenance throughout the big data analysis lifecycle, which helps establish and preserve data accuracy and quality
- DEither way, a method of data reconciliation is required or the dataset representing the correct value needs to be determined
194Query Engine
- ACommon processing functions performed by a ______ include sum,average, group by join and sort
- BUnder the hood, the ________ seamlessly transforms user queries into the relevant low-level code that can be used by the processing engine
- CThe use of ________ can reduce development time and enables the manipulation of large datasets without the need to write complex programming logic
- Dbased on the business requirements documented, it can be determined whether the business problems being addressed are really Big Data problems
195Analytics Engine
- AThe ________ mechanism is able to process advanced statistical and machine learning algorithms in support of analytics processing requirements, including the identification of patterns and correlations
- BIt generally uses the processing engine mechanism to run algorithms on large datasets.
- CA _______ database generally provides an API-based query interface, rather than the SQL Interface
- DA ________ generally provides only one of the listed functions
196Analytics Engine
- AAn ________ is employed when the comparatively simple data manipulation functions of a query engine are insufficient
- BSome propietary ________ also provide specialized data analysis features, such as text analytics and machine log analysis processing
- CHow the data is grouped depends on the type of algorithm used. Each algorithm uses a different technique to identify ______
- DThis is a traditional data analysis principle that claims that data held in a reasonably sized dataset provides the maximum value
197Workflow Engine
- AA ___________ provides the ability to design and process a complex sequence of operations that can be triggered either at set time intervals or when data becomes available
- BThe workflow logic processed by a _____________ mechanism can involve the participation of other big data mechanism
- CStrategic BI and analytics fall in this category, since they are highly read intensive task involving large volumes of data
- DLaw of large numbers
198
Workflow Engine- AFor example, a __________ can execute logic that collects relational data from multiple databases at regular intervals via the data transfer engine mechanism, applies a set of ETL operations via the processing engine mechanism and finally persists the results to a NoSQL storage device
- BThe defined workflows are analogous to a flowchart with control logic (such as decisions, forks, joins) and generally rely on a batch-style processing engine for execution
- CThe output of one workflow can become the input of another workflow
- Dit can be based on either supervised or unsupervised learning
199Coordination Engine
- AA distributed Big Data solution that needs to run on multiple servers relies on the coordination engine mechanism to ensure operational consistency across all of the participating servers
- Bmake it possible to develop highly reliable, highly available distributed big data solutions that can be deployed in a cluster
- CA model look like a mathematical equation or a set of rules
- Ddata that appears to be invalid may still be valuable in that it may possess hidden patterns and trends
200Coordination Engine
- Athe processing engine mechanism will often use the ___________ to coordinate data processing across a large number of servers. This way, the processing engine does not require its own coordination logic
- BThe ________ mechanism can also be used for support distributed locks, support distributed queues, establish a highly available registry for obtaining configuration information, reliable asynchronous communication between processes that are running on different servers
- Cin the case of realtime analytics, the data is analyzed first and then persisted to disk
- DBig Data solutions require a distibuted processing environment that can accomodate large-scale data volumes, velocity and variety
Information
- Description
- Modulo 2
- Author
- Juan Taborda
- Language
- Español
- Views
- 199
- Tags
- Rating
- No ratings yet Rate this quiz