Scribd
Upload
78 views

Ch3 - Introduction To Big Data Analytics

This document discusses big data and data analytics. It defines different types of data structures like structured, semi-structured, and unstructured data. It also outlines the emerging big data ecosystem and key roles needed like data scientists, data savvy professionals, and technology enablers.

Uploaded by

Alhanouf
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
78 views

Ch3 - Introduction To Big Data Analytics

This document discusses big data and data analytics. It defines different types of data structures like structured, semi-structured, and unstructured data. It also outlines the emerging big data ecosystem and key roles needed like data scientists, data savvy professionals, and technology enablers.

Uploaded by

Alhanouf
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 37

1

Chapter 3
Introduction to Big Data Analytics
Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing
and Presenting Data.
Contents
2

⚫ Big Data Overview


⚫ Data Structures
⚫ Bl Versus Data Science
⚫ Current Analytical Architecture
⚫ Drivers of Big Data
⚫ Emerging Big Data Ecosystem and a New
Approach to Analytics
⚫ Key Roles for the New Big Data Ecosystem
⚫ Examples of Big Data Analytics
Data Deluge
3

o Vast amounts of data


are collected daily.

o We live in the
information age

o Information leads to
power and success,
analyzing such data
is an important need
Data Deluge
4

o Data is created constantly, and at an ever-increasing


rate.
o mobile phones, imaging technologies (medical diagnosis),
devices, and sensors.
o un-traditional sources:
social media and genetic sequencing

o Difficult to
o Keep up with this huge influx of data
o more challenging is analyzing vast amounts

o Does not conform to traditional notions of data


structures
Big Data Industries
5

Several industries have led the way in developing their


ability to gather and exploit data:
 Credit card companies:
identify fraudulent purchases.

 Mobile phone companies:


analyze subscribers’ calling patterns.

 LinkedIn and Facebook:


data itself is their primary product.
Big Data Characteristics
6

1. Huge volume:
billions of rows and millions of columns.

2. Complex types and structures:


variety of new data sources, formats, and
structures,

3. Speed of creation and growth:


high velocity data, with rapid data ingestion and
near real-time analysis.
Big Data 3Vs
7
Data Structures
8
Increasing
Growth

More
Structured
Data Structures
9

 Most of the Big Data is:


 unstructured
 semi-structured in nature (80-90% of future data growth)
E.g. financial data, text files, multimedia files, and genetic
mappings.
 Need different techniques and tools:
distributed computing and parallel processing
Data Structures
10

1. Structured data:
• A predefined data type, format, and structure
• Therefore, straightforward to analyse
• Conforms to a tabular format with relationship
between the different rows and columns.
• The most traditional form of data storage
• Example: Excel files or SQL databases, transaction data.
Structured Data: Example
11
Data Structures
12

2. Semi-structured data:
• Textual data files with a pattern that enables parsing.
• A form of structured data that contains tags or other
markers to separate semantic elements and enforce
hierarchies of records and fields within the data.
Examples of semi-structured data include
• Easier to analyse than unstructured data.
• Example: XML, JSON
Semi-Structured Data: Example
13
Data Structures
14

3. Quasi-structured data:
• Textual data with erratic data formats that can be
formatted with effort, tools, and time.
• Example: web clickstream data.
Quasi-structured Data: Example
15
Data Structures
16

4. Unstructured data:
• No inherent structure; does not have a predefined
composition
• Typically text-heavy, but may contain dates, numbers, and
facts, resulting in irregularities and ambiguities
• Difficult to understand and analyse using traditional
programs
• Example: PDFs, images, and video.
Unstructured Data: Example
17
Business Drivers
18
Business Intelligence (BI)
Versus Data Science
19

Current Analytical Architecture


Typical Analytical Architecture
20
Emerging Big Data ecosystem
21

Four main groups of players within an interconnected web:


Emerging Big Data ecosystem
22

(1) Portrays Data Devices and the “Sensornet”, which is collecting data from
multiple locations and is continuously generating new data about this data.
smart phone -> busy roads, Shopping loyalty cards ->  promotions
(2) Data Collectors include entities who are collecting data from the device
and users.
TV provider -> TV content , shopping carts with RFID chip -> products
(3) Data Aggregators make sense of the data collected from the various
entities from the “SensorNet” or the “Internet of Things”. 
sell to brokers
(4) At the outer edges of this web of the ecosystem are Data Users & Buyers.
These groups directly benefit from the information.
Banks -> demographics of people with a specific threshold of debt and
searching the web for home remodeling
Key Roles of the Data Ecosystem
23

The Big Data ecosystem demands 3 categories of roles:


● Deep Analytical Talent: People with advanced skills in quantitative
disciplines; mathematics, statistics, and machine learning.
● Data Savvy Professionals: People with less technical depth but has
a basic knowledge of statistics or machine learning. They can define
key questions answered using advanced analytics. E.g. financial
analysts, market research analysts, life scientists, operations managers,
and business and functional managers.
● Technology and Data Enablers: People with skills related to
computer engineering, programming, and database administration.
They provide technical expertise to support analytical projects, such as
provisioning and administrating analytical sandboxes, and managing
large-scale data architectures.
Key Roles of the Data Ecosystem
24

The Big Data ecosystem demands 3 categories of roles:


Data Scientist Activities
25

 Reframe business challenges as analytics


challenges

 Design, implement, and deploy statistical


models and data mining techniques on Big
Data

 Develop insights that lead to actionable


recommendations.
Profile of Data Scientist
26

Data scientists generally have five main


sets of skills and behavioral characteristics:

 Quantitative skill
e.g., math, statistics
 Technical aptitude
e.g., software engineering,
programming
 Critical thinking
ability to examine work
critically
Profile of Data Scientist
27

Data scientists generally have five main


sets of skills and behavioral characteristics:

 Curious and creative


passionate about data and
finding creative solutions
 Communicative and
collaborative
can articulate ideas, can
work with others
Types of Data Analytics
28
Descriptive Analytics
29

1. Descriptive Analytics: What is happening?


 Most common
 Provides the analyst with a view of key metrics and
measures within the company/organization
 Utilizing effective visualization tools enhances the message
of descriptive analytics
 Example
⚪ Understanding demographic information on their
customers (e.g., 30% of our customers are self-employed)
would be categorized as “descriptive analytics”.
Diagnostic Analytics
30

2. Diagnostic Analytics: Why is it happening?


 Next step of complexity in data analytic
 The analyst drills down to identify anomalies and
isolates the root-cause of a problem
 Example
⚪ Why sales have increased in a region where there was
no change in marketing
Predictive Analytics
31

3. Predictive Analytics: What is likely to happen?


 All about forecasting; likelihood of an event happening
in future, forecasting a quantifiable amount, estimating a
point in time at which something might happen
 Predictive models typically utilise a variety of variable
data to make the prediction
 In a world of great uncertainty, being able to predict allows
one to make better informed decisions.
 Example
⚪ The older a person, the more susceptible they are to a heart-
attack – we would say that age has a linear correlation
with heart-attack risk).
Prescriptive Analytics
32

4. Prescriptive Analytics: What do I need to do?


 Prescriptive models utilises an understanding of what
has happened, why it has happened and a variety of
“what-might-happen” analysis to determine the next
course of action
 Example:
⚪ Producing an exam time-table such that no students have
clashing schedules.
⚪ A traffic application that chooses the best route home taking
into account the distance of each route, the speed at which
one can travel on each road and, crucially, the current traffic
constraints.
Examples of Big Data Analytics
33

Target: U.S. retailer


 Used Big Data and advanced analytical methods to drive
new revenue
 Analyzed: consumer-purchasing behavior
 Found: they made a great
deal of money from certain
life-events; marriage,
divorce, pregnancy
 The most lucrative of
these life-events is
pregnancy!
Examples of Big Data Analytics
34

● Target knew a female shopper was pregnant even before her


family knew => offer specific coupons and incentives to their
pregnant shoppers
● In which month of pregnancy a shopper may be? => manage
inventory, knowing when demand for specific products

Read more: The Power of Habit: Why We Do What We Do in Life and Business
Churn Analysis
35

• Churn prediction is one of the most popular Big Data use cases in
business.
• It consists of detecting customers “who are likely to cancel a
subscription to a service.”
• It works based on how customers use the service.
• It asks the following question for each current customer: “Is this
customer going to leave us within the next X months?”
• There are only two possible answers, yes or no, and it is what we
call a binary classification task.
Churn Analysis for Mobile Teleco
36
Using Social Network Analysis to
Improve Churn Prediction
37

You might also like