Big Data Analytics

Government Arts and Science College

Tittagudi-606106
Department of Computer Science

DECS 43A – Big Data Analysis

II Year IV Semester

Unit - 2
Big Data Analytics
Dr. S. P. Ponnusamy
Assistant Professor and Head

1
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Unit - 2
Big Data Analytics
 Overview of business intelligence
 Data science and Analytics
 Meaning and Characteristics of big data analytics
 Need of big data analytics
 Classification of analytics
 Challenges to big data analytics
 Importance of big data analytics
 Basic terminologies in big data environment

2
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Overview of business intelligence

Definition
• There is no unique or mathematical definition of Business Intelligence
• The Data Warehousing Institute defines Business Intelligence as…
 The process, technologies and tools needed
 to turn data into information,
 information into knowledge and
 knowledge into plans that drive profitable business action.
 Business intelligence encompasses data warehousing, business analytics
tools, and content/knowledge management.

3
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Overview of business intelligence

4
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Overview of business intelligence

• BI systems aggregate data from many sources
• The data needs to be cleaned and harmonized
• Some of this can be automated but human eyeballs are still
needed to verify data
• A million dollar BI system can give you incorrect data…which
drives incorrect decisions, business srtategies, actions, etc.
• When creating a BI system all the idiosyncrasies of developers,
knowledge workers and managers will see the light of day.

5
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Overview of business intelligence – Why Important?

• Business Intelligence (BI) collects the necessary data, analyzes it, and determines which
actions need to be taken, helping businesses to answer questions and track the
performance against these goals.
• Companies can take advantage of the comprehensive view of the organization's data and
then use that data to drive change, reduce inefficiencies and quickly adapt to changes.
• With BI, companies can make smarter, data-driven decisions.
• They can analyze customer behavior and even compare their data with competitors,
helping companies run smoothly and efficiently.
• BI allows companies to enhance productivity, increase revenue, accelerate business
growth and ensure higher profits.
• Implementing BI systems in an organization can reduce the time spent by
workers/executives in processing and analyzing the data while also eliminating any
errors. 6
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Overview of business intelligence – How Works?

• Companies need to analyze the data correctly to understand customer
behavior, improve operations, optimize the supply chain, etc.
• Taking into consideration the type, volume, and velocity of the data,
Business Intelligence (BI) systems can be implemented by companies
so that they will be able to use this data in the right way.
• Business intelligence combines business analytics, data mining, data
visualization, data tools, and infrastructure, which offer access to
accurate, comprehensible, and actionable information on demand,
enabling organizations that deal with a lot of data to make informed
business decisions.
7
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Overview of business intelligence

• Advantages
 Transformation of Data
 Aids in Decision-making
 Evidence-based decision making
• Disadvantages
– Accumulation of Historical Data
– Complexity
– Cost

8
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Overview of business intelligence

9
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Overview of business intelligence

Stages of BI

 Raw Data
 Data Storage Warehouse
 Access, Analyze, and Present
 Data Dashboarding and Reporting

10
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Overview of business intelligence

11
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Overview of business intelligence

Big Data Analytics Business Intelligence

Business Intelligence organizes data with the help of computer-

Leverages big data to analyze structured and unstructured based techniques and technologies to create business
data to generate insights. intelligence systems that are used for online data visualization,
reporting and analysis.

It collects data from different sources, processes it in a way

BI accesses and analyses information to improve and optimize
that it becomes available to analysts, helping businesses use
business decisions and performance.
it to their benefit.
In the Big Data environment, data is stored on a distributed
file system and not on a central server. This data is then Business Intelligence combines all business data sets into a
distributed across the worker nodes to enable easy central server. This data is stored in a platform called the data
processing. Distributed File System is much safer and warehouse.
flexible than storing the data in a data warehouse.
Big Data Analytics can be used in various industries, such as
Business Intelligence can be used in various industries, such as
Banking, Entertainment, Social Media, Healthcare,
Healthcare, Social Media, Gaming, etc.
Retail/Wholesale, etc.

12
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Data Science & Analytics

13
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Data Science
• Data Science is the process of :
 Collecting raw data from multiple disparate data sources.
 Processing the data.
 Integrating the data and preparing clean datasets.
 Engaging in explorative data analysis using model and
algorithms.
 Preparing presentations using data visualizations (commonly
called Infographics, or BizAnalytics, or VizAnalytics, etc.)
 Communicating the findings to all stakeholders.
 Making faster and better decisions.
14
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Data Scientist

15
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Data Scientist Lifecycle

Do I have enough
1
information to
Discovery draft an analytic
plan?

6 2 Do I have
Operationalize Data Prep enough “good”
data to start
building the
model?
5 3
Communicate Model
Results Planning
Is the model robust 4 Do I have a good idea about
enough? Have we Model
the type of model to try? Can
failed enough? Building
I refine the analytic plan?
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Business Intelligence versus Data Science (Advanced Analytics)

Data Science (Advanced Analytics)
Typical •Optimization, Predictive modeling, forecasting
Techniques statistical analysis
and Data •Structured/unstructured data, any types of sources,
Types very large data sets
High
•What if…?
Common •What’s the optimal scenario for our business?
Questions •What will happen next? What if these trends continue?
Why is this happening?
BUSINES

Data
VALUE

Science
Business Intelligence
S

Typical •Standard and ad hoc reporting, dashboards, alerts,

Techniques queries, details on demand
and Data •Structured data, traditional sources, manageable data
Types sets
Business
Intelligence •What happened last quarter?
Common •How many did we sell?
Low Questions
•Where is the problem? In which situations?
Past Future
TIME
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

BI Analyst Versus Data Scientist Responsibilities

Area BI Analyst Data Scientist
Focus Reports, KPIs, trends Patterns, correlations, models

Process Static, comparative Exploratory, experimentation, visual

Data sources Pre-planned, added slowly Chosen on the fly, on-demand

Transformation Up front, carefully planned ELT, on-demand, in-database, enrichment

Data quality Single version of truth Tolerant of “good enough”; probabilities

Data model Logical / relational / formal Conceptual / semantic / informal

Results Report what happened Predict what will happen

Analysis Hindsight Forecast, Insight

Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Big Data Analytics – What?

• Big data analytics sets the stage for better and faster
decision making.
• It is about leveraging technology to help with analytics.
• It spells a tight handshake between the communities of
business users, IT and data scientists.
• It when properly utilized leads to gaining a richer,
deeper and wider insights into the business, the
customers and the partners.

19
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Big Data Analytics – What?

20
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Big Data Analytics – What isn’t?

• Big data analytics is not here to replace RDBMS or data

warehouse.
• It is much more than technology.
• It is about dealing with not just the massive onslaught of
huge volumes of data but also dealing with great variety
and velocity of data.
• It works on the philosophy of “move code to data”.

21
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Big Data Analytics – What isn’t?

22
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Need of Big Data Analytics

23
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Big Data Analytics - Need

24
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Classification of analytics

25
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Big Data Analytics – Version

 Analytics 1.0  deals with historical data

to report on events, occurrences of the
past.
 Analytics 2.0  helps to predict what will
happen in future
 Analytics 3.0  is about predicting what
will happen and to best leverage the
situation when it happens. 26
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Big Data Analytics

• Descriptive analytics – (What happened?)
 Descriptive analytics is a statistical method that is used to search and summarize
historical data in order to identify patterns or meaning.
• Diagnostic analytics – (Why did this happen?)
 It is the process of using data to determine the causes of trends and
correlations between variables.
• Predictive analytics – (What might happen in the future?)
 Predictive Analytics is a statistical method that utilizes algorithms and machine
learning to identify trends in data and predict future behaviors
• Prescriptive analytics – (What should we do next?)
 Prescriptive analytics is a statistical method used to generate recommendations
and make decisions based on the computational findings of algorithmic models.
27
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

Classification of Big Data Analytics

• Descriptive analytics – (What happened?)
 Descriptive analytics is a statistical method that is used to search and summarize
historical data in order to identify patterns or meaning.
• Diagnostic analytics – (Why did this happen?)
 It is the process of using data to determine the causes of trends and
correlations between variables.
• Predictive analytics – (What might happen in the future?)
 Predictive Analytics is a statistical method that utilizes algorithms and machine
learning to identify trends in data and predict future behaviors
• Prescriptive analytics – (What should we do next?)
 Prescriptive analytics is a statistical method used to generate recommendations
and make decisions based on the computational findings of algorithmic models.
28
Big Data Analytics
Government Arts and Science College
Tittagudi-606106
Department of Computer Science

End

29