Auburn - BUAL 5650 - Final Exam
Questions and Answers
Machine Learning - Answer-Definition:
Field of study that gives computers the ability to learn without being
explicitly programmed.
Either data or experience, experience is data too. There has to be data for machines to learn without
being programmed. This is why big data is so important because machines are not as efficient as us as
learning.
Hadoop - Answer-Open source version of MapReduce first used by Yahoo. This runs the analysis on the
data stored on a hard disk.
HDFS - Hadoop Distributed File System
Spark - Answer-Runs on top of HDFS and is up to x100 faster than Hadoop, but you pay for the speed.
This runs in the memory.
Uses in Python, Scala, Java, and R.
Key Feature: Resilistent Distributed Dataset (RDD). These are fault-tolerant collections of objects that
work well with unstructured data, but forgoes some optimization and performance benefits
ETL - Answer-Extraction, Transform, Load
, Essential for a data warehouse. Extracting data from one or more sources, transforming the data from
its original form to one that is compatible with the organization's, and then loading it into the
warehouse.
ELT - Answer-Extraction, Loading, Transform. This is pulling the data from one or more sources, loading
it into the data warehouse, and then transforming the data that is needed when it is time to pull it.
Four V's - Answer-Volume - Scale of Data
Velocity - Analysis of Data, how much it generates per second for example
Variety - Different forms, what makes it structured versus unstructured, etc..
Veracity - Uncertainty of data, how much we can trust it.
Types of Business Analytics - Answer-Prescriptive - Seeks to recognize what is going on as well as the
likely forecast and to make decisions to achieve the best performance possible.
Predictive - Aims to determine what will likely happen in the future. It is based on statistical techniques.
It can use supervised learning to train predictive models
Descriptive - Reporting analytics or exploratory analytics, which refers to knowing what is happening in
an organization and understanding some underlying trends.
Business Intelligence - Answer-No universal definition, it is an umbrella term that includes databases,
applications, methodologies, and other tools used for executive and managerial decision making.
Four Types:
1. Data warehouse
2. Business Analytics
3. Business Performance Management
Questions and Answers
Machine Learning - Answer-Definition:
Field of study that gives computers the ability to learn without being
explicitly programmed.
Either data or experience, experience is data too. There has to be data for machines to learn without
being programmed. This is why big data is so important because machines are not as efficient as us as
learning.
Hadoop - Answer-Open source version of MapReduce first used by Yahoo. This runs the analysis on the
data stored on a hard disk.
HDFS - Hadoop Distributed File System
Spark - Answer-Runs on top of HDFS and is up to x100 faster than Hadoop, but you pay for the speed.
This runs in the memory.
Uses in Python, Scala, Java, and R.
Key Feature: Resilistent Distributed Dataset (RDD). These are fault-tolerant collections of objects that
work well with unstructured data, but forgoes some optimization and performance benefits
ETL - Answer-Extraction, Transform, Load
, Essential for a data warehouse. Extracting data from one or more sources, transforming the data from
its original form to one that is compatible with the organization's, and then loading it into the
warehouse.
ELT - Answer-Extraction, Loading, Transform. This is pulling the data from one or more sources, loading
it into the data warehouse, and then transforming the data that is needed when it is time to pull it.
Four V's - Answer-Volume - Scale of Data
Velocity - Analysis of Data, how much it generates per second for example
Variety - Different forms, what makes it structured versus unstructured, etc..
Veracity - Uncertainty of data, how much we can trust it.
Types of Business Analytics - Answer-Prescriptive - Seeks to recognize what is going on as well as the
likely forecast and to make decisions to achieve the best performance possible.
Predictive - Aims to determine what will likely happen in the future. It is based on statistical techniques.
It can use supervised learning to train predictive models
Descriptive - Reporting analytics or exploratory analytics, which refers to knowing what is happening in
an organization and understanding some underlying trends.
Business Intelligence - Answer-No universal definition, it is an umbrella term that includes databases,
applications, methodologies, and other tools used for executive and managerial decision making.
Four Types:
1. Data warehouse
2. Business Analytics
3. Business Performance Management
