L2: Big Data and Data Mining

Question 1

Analytics

Answer 1

The process of examining data to draw conclusions and make informed decisions is a fundamental aspect of data science, involving statistical analysis and data-driven insights.

Question 2

Big Data

Answer 2

Vast amounts of structured, semi-structured, and unstructured data are characterized by its volume, velocity, variety, veracity and value, which, when analyzed, can provide competitive advantages and drive digital transformations.

Question 3

Big Data Cluster

Answer 3

A distributed computing environment comprising thousands or tens of thousands of interconnected computers that collectively store and process large datasets.

Question 4

Broad Network Access

Answer 4

The ability to access cloud resources via standard mechanisms and platforms such as mobile devices, laptops, and workstations over networks.

Question 5

Chief Data Officer (CDO)

Answer 5

An emerging role responsible for overseeing data-related initiatives, governance, and strategies, ensuring that data plays a central role in digital transformation efforts.

Question 6

Chief Information Officer (CIO)

Answer 6

An executive is responsible for managing an organization’s information technology and computer systems, contributing to technology-related aspects of digital transformation.

Question 7

Cloud Computing

Answer 7

The delivery of on-demand computing resources, including networks, servers, storage, applications, services, and data centers, over the Internet on a pay-for-use basis.

Question 8

Cloud Deployment Models

Answer 8

Categories that indicate where cloud infrastructure resides, who manages it, and how cloud resources and services are made available to users, including public, private, and hybrid models.

Question 9

Cloud Service Models

Answer 9

Models based on the layers of a computing stack, including Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and Software as a Service (SaaS), represent different cloud computing offerings.

Question 10

Commodity Hardware

Answer 10

Standard, off-the-shelf hardware components are used in a big data cluster, offering cost-effective solutions for storage and processing without relying on specialized hardware.

Question 11

Data Algorithms

Answer 11

Computational procedures and mathematical models used to process and analyze data made accessible in the cloud for data scientists to deploy on large datasets efficiently.

Question 12

Data Replication

Answer 12

A strategy in which data is duplicated across multiple nodes in a cluster to ensure data durability and availability, reducing the risk of data loss due to hardware failures.

Question 13

Data Science

Answer 13

An interdisciplinary field that involves extracting insights and knowledge from data using various techniques, including programming, statistics, and analytical tools.

Question 14

Deep Learning

Answer 14

A subset of machine learning that involves artificial neural networks inspired by the human brain, capable of learning and making complex decisions from data on their own.

Question 15

Digital Change

Answer 15

The integration of digital technology into business processes and operations leads to improvements and innovations in how organizations operate and deliver value to customers.

Question 16

Digital Transformation

Answer 16

A strategic and cultural organizational change driven by data science, especially Big Data, to integrate digital technology across all areas of the organization, resulting in fundamental operational and value delivery changes.

Question 17

Distributed Data

Answer 17

The practice of dividing data into smaller chunks and distributing them across multiple computers within a cluster enables parallel processing for data analysis.

Question 18

Hadoop

Answer 18

A distributed storage and processing framework used for handling and analyzing large datasets, particularly well-suited for big data analytics and data science applications.

Question 19

Hadoop Distributed File System (HDFS)

Answer 19

A storage system within the Hadoop framework that partitions and distributes files across multiple nodes, facilitating parallel data access and fault tolerance.

Question 20

Infrastructure as a Service (IaaS)

Answer 20

A cloud service model that provides access to computing infrastructure, including servers, storage, and networking, without the need for users to manage or operate them.

Question 21

Java-Based Framework

Answer 21

Hadoop is implemented in Java, an open-source, high-level programming language, providing the foundation for building distributed storage and processing solutions.

Question 22

Map Process

Answer 22

The initial step in Hadoop’s MapReduce programming model, where data is processed in parallel on individual cluster nodes, often used for data transformation tasks.

Question 23

Measured Service

Answer 23

A characteristic where users are billed for cloud resources based on their actual usage, with resource utilization transparently monitored, measured, and reported.

Question 24

On-Demand Self-Service

Answer 24

The capability for users to access and provision cloud resources such as processing power, storage, and networking using simple interfaces without human interaction with service providers.

Question 25

Rapid Elasticity

Answer 25

The ability to quickly scale cloud resources up or down based on demand, allowing users to access more resources when needed and release them when not in use.

Question 26

Reduce Process

Answer 26

The second step in Hadoop's MapReduce model is where results from the mapping process are aggregated and processed further to produce the final output, typically used for analysis.

Question 27

Replication

Answer 27

The act of creating copies of data pieces within a big data cluster enhances fault tolerance and ensures data availability in case of hardware or node failures.

Question 28

Resource Pooling

Answer 28

A cloud characteristic where computing resources are shared and dynamically assigned to multiple consumers, promoting economies of scale and cost-efficiency.

Question 29

Skills Network Labs (SN Labs)

Answer 29

Learning resources provided by IBM, including tools like Jupyter Notebooks and Spark clusters, are available to learners for cloud data science projects and skill development.

Question 30

Spilling to Disk

Answer 30

A technique used in memory-constrained situations where data is temporarily written to disk storage when memory resources are exhausted, ensuring uninterrupted processing.

Question 31

STEM Classes

Answer 31

Science, Technology, Engineering, and Mathematics (STEM) courses typically taught in high schools prepare students for technical careers, including data science.

Question 32

Variety

Answer 32

The diversity of data types, including structured and unstructured data from various sources such as text, images, video, and more, posing data management challenges.

Question 33

Velocity

Answer 33

The speed at which data accumulates and is generated, often in real-time or near-real-time, drives the need for rapid data processing and analytics.

Question 34

Veracity

Answer 34

The quality and accuracy of data, ensuring that it conforms to facts and is consistent, complete, and free from ambiguity, impacts data reliability and trustworthiness.

Question 35

Video Tracking System

Answer 35

A system used to capture and analyze video data from games, enabling in-depth analysis of player movements and game dynamics, contributing to data-driven decision-making in sports.

Question 36

Volume

Answer 36

The scale of data generated and stored is driven by increased data sources, higher-resolution sensors, and scalable infrastructure.

Question 37

V's of Big Data

Answer 37

A set of characteristics common across Big Data definitions, including Velocity, Volume, Variety, Veracity, and Value, highlighting the rapid generation, scale, diversity, quality, and value of data.