Data Analytics

Landscape

6/25/22 11:59 AM 1
 Machine
Learning &
Deep
Learning
05/18/2025 2
Types of Learning
Supervised: Learning with a labeled training set
Example: email classification with already labeled emails

Unsupervised: Discover patterns in unlabeled data

Example: cluster similar documents based on text

Reinforcement learning: Learn to act based on feedback/reward

Example: learn to play Go, reward: win or lose

05/18/2025 07:38 AM 3
Machine Learning
Machine Learning is a field of computer science that gives computers the
ability to learn without being explicitly programmed
Machine Learning vs Traditional Programming

Data
Computer Output
Program
Traditional Programming

Data
Computer Program
Output
Machine Learning Approach
Machine Learning - Workflow
• Pandas
• Emoji translator • EDA
• Correlation
• Stop words • Deriving new
• Features
Removal features from
Selections
• Lemmatization available
• Sklearn
• Steaming attributes
• etc
Data Feature
Feature Selection
Preprocessing Engineering

Model Building Model Evaluation

• Kmeans, ANN, • F1- Score

Naivebayes etc. • Classification
(algo) Report
• Sklearn (lib) • Accuracy Matrixs
05/18/2025 07:38 AM • Tensorflow (lib) 6
• Sklearn(lib)
Why Machine Learning? (Importance of Machine Learning)

• Flood of available data (Especially with the advent of the internet)

• Increasing computational power
• Growing progress in available algorithms and theory developed by
researchers
• Increasing support from industries.
05/18/2025 7
Applications of Machine Learning

• Banking/Personal finance • Commuting

o Mobile check deposits o Google’s AI-Powered Predictions
o Fraud Prevention o Ride sharing apps like Uber & Lyft
o Credit Decisions • Email
• Social Networking o Spam Filters
o Facebook o Smart Email Categorization
o Pinterest • Grading & Assessment
o Instagram o Plagiarism Checkers
o Snap Chat o Robo-Readers
• Online Shopping
o Search
o Recommendations
o Fraud protection
05/18/2025 8
What is Deep Learning?

05/18/2025 9
Deep Learning

Cognition
as a
Service

Deep
Learning /
Neural
Network
GPU / Vast
Scalable Training
Computing Data

Deep learning is a compute-intensive and adaptive machine learning method that encapsulates feature
engineering and model building.

05/18/2025 07:38 AM 10
Machine Learning vs Deep Learning
• A Machine Learning subfield of learning representations of data. Exceptional effective of
learning patterns.
• Deep Learning algorithms attempt to learn (multiple levels of) representation by using a
hierarchy of multiple layers
• If you provide the system tons of information, it begins to understand it and respond in useful
ways.

05/18/2025 07:38 AM 11
Deep Learning Applications

Image Natural Speech Robots

Recognitio Language Recognitio and Self-
n Processin n Driving
g Cars

05/18/2025 12
Why Deep Learning is Useful?

• Manually designed features are often over-specified, incomplete and take a

long time to design and validate.
• Learned Features are easy to adapt, fast to learn
• Deep Learning provides a very flexible, (almost) universal, learnable
framework for representing world, visual and linguistic information.
• Can learn both unsupervised and supervised
• Utilize large amounts of training data

In 2010 DL started outperforming other ML techniques

First in speech and vision, then NLP

05/18/2025 07:38 AM 13
AI & Data Science

Vs

05/18/2025 14
 15

Artificial
Intelligence
Machine
Learning
Neural
Network
Deep
Neural
Networks
/ Deep
Big Data

Learning
Data Science
Relation Between AI & Data Science

05/18/2025 07:38 AM
Data Science Vs Artificial Intelligence Comparison Table
Data Science vs Artificial
Data Science Artificial Intelligence
Intelligence

Data Science is of curating mass data for analytics Artificial Intelligence is implementing this
Meaning
and visualization data in Machine

Algorithm technique design and

Skills Statistical technique design and development
development

Artificial Intelligence is a Machine Learning

Technique Data Science is Data Analytics Technique
technique

Use of Knowledge Data Science use statistical learning for Analysis Artificial Intelligence is of Machine Learning

Observation Patterns in Data for decision Intelligence in Data for decision

Data Science tends to use parts of this loop to solve Artificial intelligence represents the loop of
Solving specific problems perception and planning with action

05/18/2025 07:38 AM 16
Data Science Vs Artificial Intelligence Comparison Table
Data Science vs Artificial
Data Science Artificial Intelligence
Intelligence

Data Science Medium level processing of Data for Artificial Intelligence high order processing
Processing
Data Manipulation scientific data for manipulation

Data Science involved in data representation in the Artificial intelligence involve in algorithm
Graphic
various graphical format network node representation

Data Control and manipulation with Data Science Robotic control with artificial intelligence
Control
technique and machine

05/18/2025 07:38 AM 17
Data Science Hierarchy of Needs
Al
Deep
Learning
A/B Testing
Experimentatio
Learn / Optimize n, Simple ML
Algorithms
Analytics, metrics,
Aggregate / Label segments, aggregates,
features, training data

Explore / Cleaning, anomaly detection

Transform
Reliable Data Flow, Infrastructure,
Move/Store pipelines, ETL, Structured and
unstructured data storage

Instrumentation, Logging, Sensors, External

Collect Data, User Generated content

05/18/2025 07:38 AM 18
 Natural
Language
Processing

05/18/2025 19
What is NLP?

Natural language processing (NLP) is a field of computer

science, artificial intelligence, and computational linguistics
concerned with the interactions between computers and human
(natural) languages.

05/18/2025 20
Go Beyond The Keyword Matching

• Identify the structure and meaning of words, sentences, texts

and conversations
• Deep understanding of broad language

05/18/2025 21
Machine Translation

05/18/2025 22
System Dialog

05/18/2025 23
Sentiment/Opinion Analysis

05/18/2025 24
Text Classification

www.wired.com

05/18/2025 25
Information Extraction

Unstructured text to database entries

New York Times Co. named Russel T.lewis, 45, president and general
manager of its flagship New Yark Times newspaper, responsible for all
business-side activities. He was executive vice president and deputy
general manager. He succeeds Lance R. Primis, who is September was
named president and chief operating officer of the parent.

Person Company Post State

Russel T. Lewis New York Times newspaper President and general manager Start

Russell T. Lewis New York Times Newspaper Executive vie president End

Lance R. Primis New York Times Co. President and CEO start

05/18/2025 26
Cloud Computing

Cloud computing is the on-demand

availability of computer system
resources, especially data storage
and computing power, without direct
active management by the user. The
term is generally used to describe
data centers available to many users
over the Internet.

05/18/2025 07:38 AM 27
Why Cloud Computing?

24 * 7 Pay as you
Support Use

Reliability
Device & Scalability
Location &
Independen Sustainabili
t ty

Why Cloud
Easy & Computing
Agile ? Secure
Deploymen Storage
t

Lower
Utility Capital
Based Expenditur
e

Highly
Automated

05/18/2025 07:38 AM 28
Applications of Cloud Computing

Storing Files Online

Backup & Recovery

Business Process

E-Commerce Applications

Anti-Virus Applications

Many More
05/18/2025 07:38 AM 29
Internet of Things

The Internet of things is the extension of

Internet connectivity into physical devices
and everyday objects. Embedded with
electronics, Internet connectivity, and
other forms of hardware, these devices
can communicate and interact with
others over the Internet, and they can be
remotely monitored and controlled.

05/18/2025 07:38 AM 30
Applications of Internet of Things

Industrial
Smart Home Wearables Smart City Smart Grids
Internet

Connected Smart Supply

Connected Car Smart Retail
Health Chain

05/18/2025 07:38 AM 31
Edge Computing

Edge computing is a distributed computing paradigm which brings

computer data storage closer to the location where it is needed.
Computation is largely or completely performed on distributed device
nodes.

05/18/2025 07:38 AM 32
Benefits of Edge Computing

Interoperability
Reliable
between
Faster Operations with Security & Cost-Effective
Legacy &
Response Time intermittent Compliance Solutions
Modern
Connectivity
Devices

05/18/2025 07:38 AM 33
Applications of Edge Computing

Traffic Autonomous Grid Edge Control

Management Vehicles and Analytics

Oil & Gas Remote Edge Video

Monitoring Orchestration
05/18/2025 07:38 AM 34
6/25/22 11:59 AM 35