BIGDATA ANALYTICS

LAKSHMIKANTHA G C
BITS Pilani
Pilani Campus WILP, BITS PILANI
 BITS Pilani
Pilani Campus

Previous Session
Big Data: An Overview
Types, Characteristics, Challenges, Applications, and Lifecycle
 BITS Pilani
Pilani Campus

Big Data: An Overview

Analytics and the Big data Technology Landscape.
What is Analytics?

• Analytics is the process of transforming data into insights for decision-

making. It encompasses various techniques and tools to interpret data
patterns.

BITS Pilani, Pilani Campus

Evolution of Analytics

• Analytics has evolved from simple descriptive statistics to complex predictive

and prescriptive models, driven by advancements in data processing
technologies.

BITS Pilani, Pilani Campus

Components of Analytics

Core components include

• Data collection,

• Processing,

• Modeling, and

• Decision-making.

Effective analytics integrates these to deliver actionable insights.

BITS Pilani, Pilani Campus

Components of Analytics

Data Collection: Gathering raw data from various sources such as databases, sensors, or logs.

Processing: Cleaning and transforming raw data into a usable format for analysis.

Modeling: Applying statistical or machine learning models to derive insights or predictions from
processed data.

Decision-making: Utilizing the results from modeling to make informed decisions that can impact
business strategies or operations.

BITS Pilani, Pilani Campus

 Key Analytical Techniques

Techniques such as

• Statistical analysis,

• Data mining, and

• Machine learning are used to uncover patterns and trends in large datasets.

BITS Pilani, Pilani Campus

Types of Analytics

• Descriptive Analytics

• Diagnostic Analytics

• Predictive Analytics

• Predictive Analytics

BITS Pilani, Pilani Campus

Types of Analytics

Descriptive Analytics

• Descriptive analytics summarizes historical data to understand what has

happened in the past. Examples include sales reports that analyze previous
transactions.

BITS Pilani, Pilani Campus

Types of Analytics

Diagnostic Analytics

• Diagnostic analytics delves deeper to explain why something happened,

using techniques like data discovery and root cause analysis.

BITS Pilani, Pilani Campus

Types of Analytics

Predictive Analytics

• Predictive analytics uses statistical models and machine learning to forecast

future events based on historical data. An example is demand forecasting in
retail.

BITS Pilani, Pilani Campus

Types of Analytics

Prescriptive Analytics

• Prescriptive analytics suggests actions to achieve desired outcomes, often

using optimization techniques. For example, it can optimize supply chain
logistics.

BITS Pilani, Pilani Campus

Comparative Overview of Analytics Types

• Each type of analytics builds on the previous one, offering increasing levels
of insight, from what happened to what should be done.

BITS Pilani, Pilani Campus

Big Data Analytics

Introduction to Big Data Analytics

• Big Data Analytics involves processing vast amounts of data to uncover hidden patterns and
correlations that traditional analytics might miss.

Importance of Big Data Analytics

• Big data analytics provides a competitive edge by enabling real-time decision-making and
deeper insights into customer behavior.

Differences Between Traditional and Big Data Analytics

• Big Data Analytics differs from traditional methods in its ability to scale and process
unstructured data from diverse sources.
BITS Pilani, Pilani Campus
Big Data Analytics

Challenges in Big Data Analytics

• Major challenges include data quality, integration, and scalability. Effective
solutions involve robust data management and processing frameworks.

Big Data Analytics Use Cases

• Industries such as healthcare and finance use big data analytics for
personalized services and risk management. For example, predictive
maintenance in manufacturing.
BITS Pilani, Pilani Campus
Big Data Technology Landscape

Overview of Big Data Technologies

• The big data technology landscape includes tools for data management,
processing, and visualization, each playing a critical role in handling large
datasets.

BITS Pilani, Pilani Campus

Big Data Technology Landscape

Hadoop Ecosystem
• Hadoop, with its core
components HDFS,
MapReduce, and YARN, is
foundational for big data
processing. It allows scalable
storage and processing of
large datasets.

BITS Pilani, Pilani Campus

Big Data Technology Landscape

NoSQL Databases
• NoSQL databases like
MongoDB handle large
volumes of unstructured
data.
• These are essential for
applications needing flexible
and scalable data storage
solutions.

BITS Pilani, Pilani Campus

Big Data Technology Landscape

Data Warehousing Solutions

• Big data warehousing, such as

Apache Hive, supports the
storage and querying of large
datasets, differing from traditional
data warehouses in scalability
and speed.

BITS Pilani, Pilani Campus

Big Data Technology Landscape

Real-Time Data Processing

• Tools like Apache Kafka

enable low-latency data
processing, crucial for real-
time analytics in sectors like
social media and financial
trading.

BITS Pilani, Pilani Campus

Big Data Technology Landscape

Data Integration and ETL Tools

• ETL tools, including Apache NiFi,

streamline data integration by
automating the extraction,
transformation, and loading of
data from multiple sources.

BITS Pilani, Pilani Campus

Big Data Technology Landscape

Big Data Analytics Frameworks

• Apache Spark provides in-

memory processing, significantly
speeding up big data analytics
tasks, especially for machine
learning models.

BITS Pilani, Pilani Campus

Big Data Technology Landscape

Cloud Solutions for Big Data

• Cloud platforms such as AWS,

Google Cloud, and Azure offer
scalable solutions for big data
storage and analytics, enabling
organizations to handle vast
data efficiently.

BITS Pilani, Pilani Campus

Integrating Big Data and Analytics

End-to-End Big Data Analytics

Pipeline

• A comprehensive pipeline
includes data ingestion, storage,
processing, analysis, and
visualization. For example,
creating a customer 360 view
integrates multiple data sources.

BITS Pilani, Pilani Campus

Integrating Big Data and Analytics

The Role of Machine Learning in

Big Data Analytics
• Machine learning enhances big
data analytics by enabling the
development of predictive
models that can analyze
complex patterns in large
datasets.

BITS Pilani, Pilani Campus

Integrating Big Data and Analytics

Advanced Analytics Techniques

• Techniques like text analytics and sentiment analysis are essential for
extracting insights from unstructured data, such as social media feeds.

BITS Pilani, Pilani Campus

Integrating Big Data and Analytics

Implementing Big Data Analytics

• Implementation involves identifying the right use case, selecting appropriate

tools, and iterating through data processing and visualization.

BITS Pilani, Pilani Campus

Integrating Big Data and Analytics

Big Data Security and Privacy

• Ensuring data security and privacy is crucial in big data analytics. Techniques
like encryption and access control are essential to protect sensitive data.

BITS Pilani, Pilani Campus

Integrating Big Data and Analytics

Case Study 1: Big Data in Healthcare

• Big data analytics in healthcare, such as analyzing patient records and

genomic data, can lead to personalized medicine and more effective
treatments.

BITS Pilani, Pilani Campus

Integrating Big Data and Analytics

Case Study 2: Big Data in Retail

• In retail, big data analytics is used for customer segmentation and targeted
marketing, improving customer experiences and sales.

BITS Pilani, Pilani Campus

Emerging Trends and Future of Big Data
Analytics

AI and Big Data Analytics

• AI is increasingly integrated with big data analytics to process and analyze

large datasets, enabling more accurate and automated decision-making.

BITS Pilani, Pilani Campus

Emerging Trends and Future of Big Data
Analytics

IoT and Big Data

• The Internet of Things (IoT) generates vast amounts of data that big data
analytics processes for applications like smart cities and real-time monitoring.

BITS Pilani, Pilani Campus

Emerging Trends and Future of Big Data
Analytics

Edge Computing in Big Data Analytics

• Edge computing processes data closer to the source, reducing latency and
enabling real-time analytics, essential for applications like autonomous
vehicles.

BITS Pilani, Pilani Campus

Emerging Trends and Future of Big Data
Analytics

Blockchain and Big Data

• Blockchain technology can enhance data security in big data analytics,

providing a transparent and immutable record of transactions.

BITS Pilani, Pilani Campus

Emerging Trends and Future of Big Data
Analytics

Future Challenges in Big Data Analytics

• Challenges like data overload and infrastructure costs need strategic

solutions, including advancements in data processing technologies.

BITS Pilani, Pilani Campus

Emerging Trends and Future of Big Data
Analytics

The Road Ahead: Big Data and Business Strategy

• Big data must be aligned with business strategy to drive innovation and
maintain a competitive edge, as illustrated by companies leveraging data for
strategic advantage.

BITS Pilani, Pilani Campus

Conclusion

Recap of Key Takeaways

BITS Pilani, Pilani Campus

BITS Pilani, Pilani Campus