Big Data

Analytics
GROUP 12

University Roll No. Name

11500221052 Shuvam Pal

11500221054 Hrishikesh Kumar Chaudhary

11500221055 Ishika Rana

11500221056 Dipanjan Saha

What is big data?
“Big Data refers to data volumes in the range of
exabytes and beyond”

1. Sam Madden from Massachusetts Institute of

Technology (MIT) considers” Big Data” to be
data that is too big, too fast, or too hard for
existing tools to process.

2. It refers to the massive amounts of data that

is collected over time that are difficult to
analyze and handle using common database
management tools.
 Structured data refers to highly organized
information that is easily searchable and typically
● Textual content stored in relational databases or spreadsheets. It
● Multimedia content adheres to a rigid schema, meaning each data ● Customer names and
● Data from IoT element is clearly defined and accessible in a addresses in a CRM
devices fixed field within a record or file. system
● Transactional data
Structured Data ● Employee data

Unstructured data lacks a pre-defined data

model, making it more difficult to collect, process
and analyze. It comprises the majority of data Semi-structured data occupies the middle ground
generated today, and includes formats such as: between structured and unstructured data. While
it does not reside in a relational database, it
Unstructured Data ● JSON (JavaScript Object contains tags or other markers to separate
Notation) and XML semantic elements and enforce hierarchies of
(eXtensible Markup records and fields within the data.
Language) files
● Email
Semi-structured data
● NoSQL databases

Types of big data

 Big Data Analytics
Big data analytics refers to the systematic
processing and analysis of large amounts of
data and complex data sets, known as big data,
to extract valuable insights. Big data analytics
allows for the uncovering of trends, patterns
and correlations in large amounts of raw data to
help analysts make data-informed decisions.

This process allows organizations to leverage

the exponentially growing data generated from
diverse sources, including internet-of-
things (IoT) sensors, social media, financial
transactions and smart devices to derive
actionable intelligence through advanced
analytic techniques.
 How big data analytics works
1. Collect Data 2. Process Data 3. Clean Data 4. Analyze Data
• Data collection looks • Once data is collected • Data big or small requires • Getting big data into a
different for every and stored, it must be scrubbing to improve usable state takes time.
organization. With organized properly to get data quality and get Once it’s ready, advanced
today’s technology, accurate results on stronger results; all data analytics processes can
organizations can gather analytical queries, must be formatted turn big data into big
both structured and especially when it’s large correctly, and any insights. Some of these
unstructured data from a and unstructured. duplicative or big data analysis
variety of sources • Batch processing, which irrelevant data must be methods include:
• Raw or unstructured data looks at large data blocks eliminated or accounted
that is too diverse or over time. for. • Data mining
complex for a warehouse • Stream processing • Dirty data can obscure • Predictive analytics
may be assigned looks at small batches of and mislead, creating • Deep learning
metadata and stored in a data at once, shortening flawed insights.
data lake. the delay time between
collection and analysis
for quicker decision-
making.
Volume Value
The sheer volume of data Big data analytics aims to
generated today, from social
media feeds, IoT devices,
The five V's of extract actionable insights
that offer tangible value.
transaction records and
more, presents a significant big data This involves turning vast
data sets into meaningful
challenge. information that can inform
analytics strategic decisions.

Velocity
Veracity
The velocity at which data
flows into organizations Veracity refers to the data's
trustworthiness,
requires robust processing Variety encompassing data quality,
capabilities to capture,
process and deliver accurate Data comes in many formats noise and anomaly detection
analysis in near real-time. this variety demands flexible issues.
data management systems
to handle and integrate
disparate data types for
comprehensive analysis.
 Types of big data analytics
Descriptive analytics. Predictive analytics.
• This is the simplest form of analytics, where data is • This refers to analysis that predicts what comes next.
analyzed for general assessment and For example, this could include monitoring the
summarization. For example, in sales reporting, an performance of machines in a factory and comparing
organization can analyze the efficiency of that data to historical data to determine when a
marketing from such data. machine is likely to break down or require
maintenance or replacement.

Diagnostic analytics. Prescriptive analytics.

• This refers to analytics that determine why a • This form of analysis follows diagnostics and
problem occurred. For example, this could include predictions. After an issue has been identified, it
gathering and studying competitor pricing data to provides a recommendation of what can be done
determine when a product's sales fell off because about it. For example, this could include addressing
the competitor undercut it with a price drop. inconsistencies in supply chain that are causing
pricing problems by identifying suppliers whose
performance is unreliable, suggesting their
replacement.
 Benefits of using big data analytics

01 02 03
Real-time intelligence Better-informed Cost savings
decisions

04 05 06
Better customer Optimized risk Market insights and
engagement management Product development
strategies
 Big challenges of big data
Making big data accessible. Maintaining quality data.
Collecting and processing data becomes With so much data to maintain,
more difficult as the amount of data organizations are spending more time
grows. Organizations must make data than ever before scrubbing for
easy and convenient for data owners of duplicates, errors, absences, conflicts,
all skill levels to use. and inconsistencies.

Finding the right tools and

Keeping data secure. platforms.
As the amount of data grows, so New technologies for processing and
do privacy and security concerns. analyzing big data are developed all the
Organizations will need to strive for time. Organizations must find the right
compliance and put tight data processes technology to work within their
in place before they take advantage of established ecosystems and address
big data. their particular needs.
 Big data analytics technologies and tools

Hadoop Python and R Machine Learning

Tableau
Frameworks (e.g.,
TensorFlow)

NoSQL databases MapReduce YARN Spark

 Conclusion
Big Data Analytics is a game-changer that’s shaping a
smarter future. From improving healthcare and
personalizing shopping to securing finances and predicting
demand, it’s transforming various aspects of our lives.
However, Challenges like managing overwhelming data and
safeguarding privacy are real concerns. In our world flooded
with data, Big Data Analytics acts as a guiding light. It helps
us make smarter choices, offers personalized experiences,
and uncovers valuable insights. It’s a powerful and stable
tool that promises a better and more efficient future for
everyone.
Thank You !!
We express our profound gratitude to our mentors and members who
have provided their support and guidance and their invaluable
assistance and encouragement.

Resources
● https://journalofcloudcomputing.springe
ropen.com/articles/10.1186/s13677-
022-00301-w
● https://www.techtarget.com/searchbusi
nessanalytics/definition/big-data-
analytics
● https://www.ibm.com/topics/big-data-
analytics
● https://www.geeksforgeeks.org/what-is-
big-data-analytics/