Advanced Data Science & AI

Certification Program

300+ Hiring Hybrid Model 175% Average

Partners for Project Sessions Salary Hike

www.learnbay.co

+91 77956 87988 Learnvista Pvt. Ltd.

About the program 01

Program highlights 02

Why learn data science? 03

Program details 04

Domain electives 05

Check out what our alumni have to say 06

Career service 07

Learning path 08

Program syllabus 09

Real-time projects and case-studies 10

Certification 11

Learnvista Pvt. Ltd. www.learnbay.co +91 77956 87988

 Our Advanced Data Science and AI program is
2cr designed for professionals seeking to advance their
worth careers in the fast-changing field. It offers a holistic
scholarships
awarded learning experience with practical applications and
real-world case studies. The program covers
cutting-edge technologies and ethical
considerations in AI to prepare working
professionals for success.

600+
professionals
secured jobs We exist to provide accessible, reasonable, and
after a career industry-relevant education that empowers
break
India's workforce to grow and develop.

30k+ Thousands of student reviews on Switchup,

Trusted Course Report, Google and more
Learners
Program Highlights

Industry-Relevant & 360 Degree Knowledge

Updated Syllabus Building
Learn new tools, techniques & Develop practical skills through
trends. Gain app development real-world projects and
experience. assignments.

One on one Dedicated Multiple Career

Mentorship Opportunities
Personalized learning experience Advance in data science career
from experienced industry by pursuing roles like data
professionals. scientist, engineer, etc.
Why Learn Data Science?

60% rise in 250% highest 300+ partner

data science jobs salary hike companies

** Avg Salary in Lakhs Data Science popularity in last 5 years

Placement Report

30K+ 9K+ 50K+

Trusted Learners Successfully Placed Job Interviews Cracked

Book a free consultation with expert Contacts Us

Program Details
ELIGIBILITY

Working professional having more than 6 months of experience in any

domain (Technical/Non-Technical)

Qualification:
BE/B.Tech (from any branch), BBA/MBA, MCA/M.Tech, B.Com, B.Sc
(in any branch)

Course duration : 250+ hours

Weekday Batch : 7 months Weekend Batch : 9 months

Monday - Friday : 2 hrs/day Saturday - Sunday: 3.5 hrs/day

About instructors:

Experienced software development instructors share valuable practical

knowledge and effective solutions, preparing students for success in the
industry.

TOTAL FEES EASY EMI

₹ 99,000/- + 18% GST ₹ 9,735/month

Financing partners

₹ 1,16,820/-
Domain Electives
Select any 1 domain and become a domain expert

BFSI
Master financial analysis for
strategic development success

Healthcare
Use advanced tools & methods to
gain a competitive edge

Manufacturing
Explore advanced tech for
strategic skill development

Energy, Oil & Gas

Excel in data analysis, craft
dynamic dashboard for insights

Supply chain, E-com & Retail

Master supply chain domain with
data-driven insights and strategies
What Our Alumni's Say

Learnbay has helped me a lot to learn data science

applications in the e-commerce industry. The live
Shravanthi A class concept was really helpful in receiving proper
Data Scientist DS training. Thanks to all my mentors and the
placement team.
230%
Salary Hike

I knew nothing about data science before I joined

Learnbay. But through a variety of instructors, I
Ritesh Kumar steadily developed my notion and received solid
Associate Consultant knowledge and conceptual training in data science
with hike of 150%.
150%
Salary Hike

When I joined Learnbay I did not have any

knowledge apart from the very basics. I gradually
Saurabh Kumar build my concept via various trainers and get
Data Scientist & Statistician trained in data science with strong
knowledge/concepts.
135%
Salary Hike
What Our Alumni's Say

The course structure is excellent with emphasis on

concept building and tools & software at the same
Preksha Mishra time. The support team is excellent and supportive
Lead Data Scientist and quite agile to respond to doubts.

140%
Salary Hike

Thanks to the Learnbay data science course &

excellent guidance, I was able to ace the TCS
Mohd. Israr interview and secure a job with a 210% pay raise.
Data Scientist The real-world time projects helped me develop my
concepts as a data scientist.
210%
Salary Hike

Learnbay stands out with expert-led courses that

offer practical and up-to-date content. Hands-on
learning and ample resources make it accessible
for anyone seeking to upskill in AI, ML, or data
Sweekrithi shetty
science. Learnbay is an excellent choice to learn
and grow in these rapidly-evolving fields.
Certificates

IBM Course Certificate

Complete your training with the globally

recognized certificate.

Microsoft Course Certificate

Achieve professional growth & increase

earning potential with Microsoft
certification

IBM Capstone Project Certificate

Highlight your skills & boost your project

portfolio with capstone project certificate
Learning Path

AI Tools
Deep Learning, NLP,

05 Deployment (AWS + Azure)

Data Science Tools

Matplotlib, SQL, MongoDB, Tableau,
PowerBI, Big Data & Spark Analytics,
04 Time Series

Statistics and Machine Learning

03 Matplotlib, Scikit-Learn, Seaborn

Python Programming (Basic + Advance)

02 Python, Anaconda, Github, Pandas

01 Cohort Orientation + Special Programming Classes

 Get 1 year of Job and Placement support
Unleash your career potential with unlimited job access,
interview support, and profile review.

Get 3 mock interviews with industry leaders

Master the art of data science & AI and stay ahead of
the curve with mockups and industry insights

Resume build up session

Craft a powerful resume showcasing your expertise in
data science and AI to stand out from the competition.

Get 5-8 interview calls

Receive 5-8 interview calls from a diverse pool of
interested employers/recruiters.
Others Vs Learnbay

Benefits Learnbay Others

Guaranteed Interview
Calls

Industry capstone project

certificate from IBM

Domain specialized
programs for professionals

100% live interactive sessions

with industry experts

On demand video call

with industry experts

Personalized Resume
Review Session
 TERM 1
Program Syllabus

Preparatory Session Module 0 (08 hours)

Preparatory Session Fundamentals of programming

A brief introduction to tools related to Types of code editors in python

data Introduction to Anaconda & Jupyter
Learn about particular real-time notebook
projects and Capstone projects Flavors of python
Data and its impact on career Introduction to Git, GitHub
opportunities Python Fundamentals
Fundamental relevance of projects Source code vs Byte code vs Machine
using data code
Role of data in businesses Compiler & Interpreter
Significance of data in decision- Memory Management in Python
making
Scope of data in research and
development
Utilizing data, to enhance industrial
Tools covered
operations and management
Data in performance evaluation
Data in customer segmentation

Fundamentals of Statistics

Mean, Median, Mode

Standard Deviation, Average.
Probability, permutations, and
combinations
Introduction to Linear Algebra
 TERM 1
Program Syllabus

Python Programming Module 1 (50 hours)

Programming Basics & Environment Python Programming Overview

Setup Python Overview
Installing Anaconda, Anaconda Basics Python 2.7 vs Python 3
and Introduction Writing your First Python Program
Get familiar with version control, Git Lines and Indentation, Python
and GitHub. Identifiers
Basic Github Commands. Various Operators and Operators
Introduction to Jupyter Notebook Precedence
environment. Basics Jupyter notebook Getting input from User, Comments,
Commands. Multi line Comments
Programming language basics

Python Data Types

Strings, Decisions & Loop Control List, Tuples, Dictionaries

Python Lists, Tuples, Dictionaries
Working With Numbers, Booleans
Accessing Values, Basic Operations
and Strings, String types and
Indexing, Slicing, and Matrixes
formatting, String operations
Built-in Functions & Methods
Simple if Statement, if-else Statement
Exercises on List, Tuples And
if-elif Statement.
Dictionary
Introduction to while Loops, for
Loops, Using continue and break

Class Hands-on:
6 programs/coding exercise on string, Functions And Modules

loop and conditions in classroom Anonymous Functions - Lambda

Using Built-In Modules, User-Defined
Modules, Module Namespaces,
Functions And Modules Iterators And Generators

Introduction To Functions Class Hands-on:

Defining & Calling Functions 8+ Programs to be covered in class of
Functions With Multiple Arguments functions, Lambda, modules, Generators
and Packages.
 TERM 1
Program Syllabus

Python Programming Module 1 (50 hours)

File I/O An d Exceptional Handling and Data Analysis Using Numpy

Regular Expression Introduction to Numpy. Array
Opening and Closing Files Creation, Printing Arrays, Basic
open Function, file Object Attributes Operation - Indexing, Slicing and
close() Method, Read, write, seek. Iterating, Shape Manipulation -
Exception Handling, try-finally Clause Changing shape, stacking and
Raising an Exceptions, User-Defined splitting of array
Exceptions Vector stacking, Broadcasting with
Regular Expression- Search and Numpy, Numpy for Statistical
Replace Operation
Regular Expression Modifiers
Regular Expression Patterns
Assignment 1 (Week 2):
Class hands-on :
10 Coding exercises on Python
10+ Programs to be covered in class
Basics - Variables, Operators,
from File IO, Reg-ex and exception
Strings, Loops, Control Statement
handling.
Assignment 2 (Week 3):

10 Python programs and practice

set on List, Tuples, Dictionaries &
Data Analysis Using Pandas Matrices operations

Pandas : Introduction to Pandas Assignment 3 (Week 4):

Importing data into Python 10 Coding exercises on Functions,
Pandas Data Frames, Indexing Data Lambda, Input-Output, File and
Frames ,Basic Operations With Data Regular Expression
frame, Renaming Columns,
Subsetting and filtering a data frame.
 TERM 1
Program Syllabus

Python Programming Module - 1 (50 hours)

Data Visualization using Matplotlib Data Visualization using Seaborn

Matplotlib: Introduction, plot(), Seaborn: Intro to Seaborn And

Controlling Line Properties, Subplot Visualizing statistical relationships ,
with Functional Method, Multiple Plot, Import and Prepare data. Plotting
Working with Multiple Figures, with categorical data and Visualizing
Histograms linear relationships.
Seaborn Exercise

Case Study

3 Case Study on Numpy, Pandas, Matplotlib

1 Case Study on Pandas And Seaborn

Assessment Test in Python :

2 hour of Assesment Test in Python (

Coding & Objective Questions )

Real time Use cases in Python to be Covered in Class with 5 assignments

 TERM 2
Program Syllabus

Statistics Module - 1 (30 hours)

Fundamentals of Math and Probability All about Population & Sample

Probability distributed function & Population vs Sample, Sample Size

cumulative distribution function. Simple Random Sampling, Systematic
Conditional Probability, Baye’s Sampling, Cluster Sampling, Stratified
Theorem Sampling, Convenience Sampling,
Problem solving for probability Quota Sampling, Snowball Sampling
assignments and Judgement Sampling
Random Experiments, Mutually
Exclusive Events, Joint Events,
Dependent & Independent Events
Descriptive Statistics

Measures of Central Tendency –

Mean, Median and Mode
Introduction to Statistics, Statistical
Measures of Dispersion – Standard
Thinking
Deviation, Variance, Range, IQR (Inter-
Variable and its types Quartile Range)
Quantitative, Categorical, Discrete, Measure of Symmetricity/ Shape –
Continuous, Skewness and Kurtosis
*all with examples

Five Point Summary and Box Plot

Outliers, Causes of Outliers, How to Inferential Statistics

treat Outliers, I-QR Method and Z-
Characteristics of Z-distribution and
Score Method
T-Distribution.
Type of test and rejection region.
Type of errors in Hypothesis Testing
Inferential Statistics

Central Limit Theorem

Point estimate and Interval estimate
Creating confidence interval for
population parameter
 TERM 2
Program Syllabus

Statistics Module - 1 (30 hours)

Hypothesis Testing Linear Algebra

Type of test and Rejection Region Dot Product, Projecting Point on Axis.
Type o errors-Type 1 Errors, Type 2 Matrices in Python, Element Indexing,
Errors. P value method, Z score Square Matrix, Triangular Matrix,
Method. The Chi-Square Test of Diagonal Matrix, Identity Matrix,
Independence. Addition of Matrices, Scalar
Regression. Factorial Analysis of Multiplication, Matrix Multiplication,
Variance. Pearson Correlation Matrix Transpose, Determinant, Trace
Coefficients in Depth. Statistical T-Test, Analysis of variance (ANOVA),
Significance and Analysis of Covariance (ANCOVA)
Null and Alternative Hypothesis One- Regression analysis in ANOVA
tailed and Two-tailed Tests, Critical Class Hands-on:
Value, Rejection region, Inference Problem solving for C.L.T Problem
based on Critical Value solving Hypothesis Testing Problem
Binomial Distribution: Assumptions solving for T-test, Z-score test Case
of Binomial Distribution, Normal study and model run for ANOVA,
Distribution, Properties of Normal ANCOVA
Distribution, Z table, Empirical Rule of
Normal Distribution & Central Limit
Theorem and its Applications

Data Processing & Exploratory Data

Analysis

What is Data Wrangling

Data Pre-processing and cleaning?
How to Restructure the data?
What is Data Integration and
Transformation
 TERM 2
Program Syllabus

Statistics Module - 1 (30 hours)

EDA

Finding and Dealing with Missing Values.

What are Outliers?
Using Z-scores to Find Outliers.
Bivariate Analysis, Scatter Plots and Heatmaps.
Introduction to Multivariate Analysis

Note: Problem-Solving Techniques and Case Studies using Statistics will be covered
in class from week 2

Statistics Assignments : Total 4 practice set and Assignments from Statistics

 TERM 2
Program Syllabus

Machine Learning Module - 2 (40 hours)

Machine Learning Introduction Data Preprocessing

Definition, Examples, Importance of Types of Missing values (MCAR, MAR,

Machine Learning MNAR) , Methods to handle missing
Definition of ML Elements: Algorithm, values
Model, Predictor Variable, Response Outliers, Methods to handle outliers:
Variable, Training - Test Split, Steps in IQR Method, Z Method
Machine Learning, Feature Scaling: Definition , Methods:
ML Models Type: Supervised Absolute Maximum Scaling, Min-Max
Learning, Unsupervised Learning and Scaler , Normalization,
Reinforcement Learning Standardization, Robust Scaling

Data Preprocessing Logistic Regression Model

Encoding the data: Definition, Definition. Why is it called the

Methods: OneHot Encoding, Mean “Regression model”?
Encoding, Label Encoding, Target Sigmoid Function, Transformation &
Guided Ordinal Encoding Graph of Sigmoid Function

K Nearest Neighbours Model

Evaluation Metrics for Classification
model Definition, Steps in KNN Model, Types
of Distance: Manhattan Distance,
Confusion Matrix, Accuracy,
Euclidean Distance, ‘Lazy Learner
Misclassification, TPR, FPR, TNR,
Model’.
Precision, Recall, F1 Score, ROC Curve,
Confusion Matrix of Multi Class
and AUC. Using Python library Sklearn
Classification
to create the Logistic Regression
Using Python library Sklearn to create
Model and evaluate the model
the K Nearest Neighbours Model and
created
evaluate the model
 TERM 2
Program Syllabus

Machine Learning Module - 2 (40 hours)

Decision Tree Model Random Forest Model

Definition, Basic Terminologies, Tree Ensemble Techniques:

Splitting Constraints, Splitting Bagging/bootstrapping & Boosting.
Algorithms: Definition of Random Forest, OOB
CART, C4.5, ID3, CHAID Score
Splitting Methods: K-Fold Cross-Validation
GINI, Entropy, Chi-Square, and
Reduction in Variance
Using Python library Sklearn to create
the Decision Tree Model and evaluate Naive Baye’s Model
the model created Definition, Advantages, Baye’s
Theorem Applicability, Disadvantages
of Naive Baye’s Model, Laplace’s
Correction, Types of Classifiers:
Hyperparameter Tuning
Gaussian, Multinomial and Bernoulli
GridSearchCV, Variable Importance. Using Python library Sklearn to create
Using Python library Sklearn to create the Naive Baye’s Model and evaluate
the Random Forest Model and the model created
evaluate the model created.
Use cases

Case Study

Business Case Study for Kart Model

Business Case Study for Random Forest
Business Case Study for SVM
To classify an email as spam or not spam using logistic Regression.
Application of Linear Regression for Housing Price Prediction
 TERM 2
Program Syllabus

Machine Learning Module - 2 (40 hours)

K Means and Hierarchical Clustering Hierarchical Clustering

Definition of Clustering, Use cases of Dendrogram, Agglomerative

Clustering Clustering, Divisive Clustering,
K Means Clustering Algorithm, Comparison of K Means Clustering
Assumptions of K Means Clustering and Hierarchical Clustering
Sum of Squares Curve or Elbow Curve Using Python library Sklearn to create
and evaluate the clustering model

Principal Component Analysis(PCA)

Support Vector Machine(SVM)
Definition, Curse of Dimensionality,
Dimensionality Reduction Technique, Model: Definition, Use Cases, Kernel
When to use PCA, Function, Aim of Support Vectors,
Use Cases Hyperplane, Gamma Value,
Steps in PCA, EigenValues and Regularization Parameter
EigenVectors, Scree Plot. Using Python library Sklearn to create
Using Python library Sklearn to create and evaluate the SVM Model
Principal Components

Summary of all Machine Learning Models and Discussion about the Capstone
Project

Note : All Machine Learning Algorithms are covered in depth with real time case
studies for each algorithm. Once 60% of ML is completed, Capstone Project will be
released for the batch.
 TERM 2
Program Syllabus

CASE STUDY Module - 2 (40 hours)

Recommendation Engine for e-commerce/retail chain

Twitter data analysis using NLP
 TERM 3
Program Syllabus

SQL Module - 1 (14 hours)

SQL and RDBMS Advance SQL

RDBMS And SQL Operations. Advance SQL Operations

Single Table Queries - SELECT, Data Aggregations and summarizing
WHERE, the data
ORDER BY, Distinct, And, OR Ranking Functions: Top-N Analysis
Multiple Table Queries: INNER, SELF, Advanced SQL Queries for Analytics
CROSS, and OUTER, Join, Left Join,
Right
Join, Full Join, Union
JSON Data & CRUD

Basics and CRUD Operation

Databases, Collection & Documents
NoSQL, HBase & MongoDB Shell & MongoDB drivers
NoSQL Databases What is JSON Data
Introduction to HBase Create, Read, Update, Delete
HBase Architecture, HBase Finding, Deleting, Updating, Inserting
Components, Storage Model of HBase Elements
HBase vs RDBMS Working with Arrays
Introduction to Mongo DB, CRUD Understanding Schemas and
Advantages of MongoDB over RDBMS Relations

Programming with SQL

Programming with SQL
Partitioning
Mathematical Functions Filtering Data
Variables Subqueries
Conditional Logic
Loops
Custom Functions
Grouping and Ordering
 TERM 3
Program Syllabus

SQL Module - 1 (14 hours)

Assignments

Working with multiple tables

Practice Joins, Grouping and Subqueries
Using GROUP BY and HAVING Clauses
Practice Aggregation Queries
 TERM 3
Program Syllabus

MongoDB Module - 2 (14 hours)

Introduction to MongoDB MongoDB (Advance)

What is MongoDB MongoDB Use cases

Characteristics and Features MongoDB Structures
MongoDB Ecosystem MongoDB Shell vs MongoDB Server
Installation process Data Formats in MongoDB
Connecting to MongoDB database MongoDB Aggregation Framework
Introduction to NoSQL Aggregating Documents
Introduction of MongoDB module Working with MongoDB Compass &
What are Object Ids in MongoDB exploring data visually
Understanding Create, Read, Update,
Delete
Schemas & Relations
Document Structure
Working with Numeric Data
Assignment
Working on Scheme Designing
Obtain the data in the
format you want by
formulating queries that are
both effective and high- Tools covered
performing.
 TERM 3
Program Syllabus

Tableau Module - 3 (14 hours)

Introduction to Tableau Visual Analytics

Connecting to data source Getting Started With Visual Analytics

Creating dashboard pages Sorting and grouping
How to create calculated columns Working with sets, set action
Different charts Filters: Ways to filter, Interactive
Filters
Forecasting and Clustering

Dashboard and Stories

Working in Views with Dashboards

Tableau (Advance)
and Stories
Working with Sheets Mapping
Fitting Sheets Coordinate points
Legends and Quick Filters Plotting Latitude and Longitude
Tiled and Floating Layouts, Floating Custom Geocoding
Objects Polygon Maps
WMS and Background Image

Hands-on Assignments
Tools covered
Connecting data source and
data cleansing
Working with various charts
Deployment of Predictive
model in visualization
 TERM 3
Program Syllabus

PowerBI Module - 4 (14 hours)

Getting Started With Power BI Programming with Power BI

Installing Power BI Desktop and Working with Time Series

Connecting to Data Understanding aggregation and
Overview of the Workflow in Power BI granularity
Desktop Filters and Slicers in Power BI Maps
Introducing the Different Views of the Scatterplots and BI Reports
Data Mode Connecting Dataset with Power BI
Query Editor Interface Creating a Customer Segmentation
Working on Data Model Dashboard Analyzing the Customer
Segmentation Dashboard

Assignments
Tools covered
Create Bar charts
Create Pie charts
Create Tree maps
Create Donut Charts
Create Waterfall Diagrams
Creating Table Calculations
for Gender
 TERM 3
Program Syllabus

Big Data & Sparks Analytics Module - 5 (16 hours)

Introduction To Hadoop & Big Data What is Spark

Distributed Architecture - A Brief Introduction to Spark RDD

Overview. Understanding Big Data Introduction to Spark SQL and Data
Introduction To Hadoop, Hadoop frames
Architecture Using R-Spark for machine learning
HDFS, Overview of MapReduce Hands-on:
Framework Installation and configuration of
Hadoop Master: Slave Architecture Spark
MapReduce Architecture Using R-Spark for machine learning
Use cases of MapReduce programming

Hands-on
Tools covered
Map reduce Use Case 1: Youtube
data analysis
Map reduce Use Case 2: Uber
data analytics
Spark RDD programming
Spark SQL and Data frame
programming
 TERM 3
Program Syllabus

Time Series Module - 6 (14 hours)

Introduction to Time Series Forecasting Introduction to ARIMA Models

Basics of Time Series Analysis and ARIMA Model Calculations, Manual

Forecasting ARIMA Parameter Selection
Method Selection in Forecasting ARIMA with Explanatory Variables
Moving Average (MA) Forecast Understanding Multivariate Time
Example Series and their Structure
Different Components of Time Series Checking for Stationarity and
Data Differencing the MTS
Log Based Differencing, Linear
Regression for Detrending

CASE STUDY

Time series classification of smartphone data to predict user behavior

Performing Time Series Analysis on Stock Prices
Time series forecasting of sales data

Note: All the assignments and case studies will be covered in-depth with real-time
examples
 TERM 4
Program Syllabus

Deep Learning Using

Tensorflow Module - 1 (20 hours)

Introduction to Deep Learning And TensorFlow Classification Examples

TensorFlow Introduction to TensorFlow
Neural Network Installing TensorFlow
Understanding Neural Network Model Simple Computation, Contents
Installing TensorFlow and Variables
Simple Computation, Constants, and Types of file formats in TensorFlow
Variables Creating A Graph - Graph
Types of file formats in TensorFlow Visualization
Creating A Graph – Graph Creating a Model - Logistic Regression
Visualization Model Building
Creating a Model – Logistic Regression TensorFlow Classification Examples
Model Building using tensor flow

Convolutional Neural Network (CNN)

Understanding Neural Networks With
Convolutional Layer Motivation
TensorFlow
Convolutional Layer Application
Basic Neural Network The architecture of a CNN
Single Hidden Layer Model Pooling Layer Application
Multiple Hidden Layer Model Deep CNN
Backpropagation – Learning Algorithm Understanding and Visualizing a CNN
and visual representation
Understand Backpropagation – Using
Neural Network Example
TensorBoard Project

Building a CNN for Image

Classification
Project on backpropagation
using Neural Networks with
Tensor Flow
 TERM 4
Program Syllabus

Natural Language Processing Module - 2 (24 hours)

Natural Language Processing Text Analysis

Text Analytics Distance Algorithms used in Text

Introduction to NLP Analytics
Use cases of NLP algorithms String Similarity
NLP Libraries Cosine Similarity Mechanism -
Need for Textual Analytics The similarity between two text
Applications of NLP documents
Word Frequency Algorithms for NLP Levenshtein distance - measuring the
Sentiment Analysis difference between two sequences

Important
KNN
Applications of Levenshtein distance
Information Retrieval Systems
LCS(Longest Common Sequence )
Information Retrieval - Precision,
Problems and solutions, LCS
Recall,F- score TF-IDF
Algorithms
KNN for document retrieval
K-Means for document retrieval
Clustering for document retrieval

Use cases on NLP

Sentiment analysis for

marketing
Toxic comments classification
Language identification
Generating research papers
titles
Application to translate and
summarize the news
RESTful API for similarity
check
 TERM 4
Program Syllabus

Deployment AWS+Azure Module - 3 (10 hours)

Introduction to AWS and Azure Setting up the Environment

Machine Learning Services
Creating AWS and Azure
Overview of AWS SageMaker and accounts
Azure Machine Learning Configuring the required tools
Key features and benefits of and SDKs (e.g. AWS CLI, Azure
using these platforms CLI, Azure PowerShell)
Understanding different types of Understanding the infrastructure
machine learning algorithms and requirements for training and
CASE STUDY
use cases deploying models (e.g. EC2
instances, GPU instances, Azure
ML Compute)

Data Preparation and Feature

Engineering
Model Training and Evaluation
Understanding the data
Choosing the right machine
requirements for machine
learning algorithm and model
learning models (e.g. structured
(e.g. regression, classification,
vs unstructured data, data size,
clustering)
data quality)
Training models using AWS
Data cleaning and preprocessing
SageMaker and Azure Machine
techniques (e.g. missing value
Learning (e.g. using built-in
imputation, feature scaling,
algorithms, custom code)
encoding categorical variables)
Evaluating model performance
Feature selection and
and tuning hyperparameters (e.g.
engineering techniques (e.g. PCA,
cross-validation, hyperparameter
feature importance)
optimization)
 TERM 4
Program Syllabus

Deployment AWS+Azure Module - 3 (10 hours)

Model Deployment and Management

Deploying trained models on AWS SageMaker and Azure Machine Learning (e.g.
creating endpoints, batch inference)
Monitoring model performance and managing versions (e.g. model drift, A/B testing)
Integration with other services and applications (e.g. AWS Lambda, Azure Functions)
techniques (e.g. PCA, feature importance)

CASE STUDY

Advanced Topics in Machine Learning on AWS and Azure

Deep learning techniques and architectures (e.g. neural networks, convolutional

neural networks, recurrent neural networks)
Natural Language Processing (NLP) use cases (e.g. text classification, sentiment
analysis, language translation)
Understanding the costs and pricing models for machine learning on AWS and Azure
(e.g. instance pricing, storage pricing, model deployment pricing)

CASE STUDY
Real-time Projects

Domain: BFSI Domain: Media

Learn and develop classification Building a content recommendation

techniques for the digital model on the basis of regional viewer
transformation of banking categorization

JPMorgan offers tax-friendly insurance Netflix is a global entertainment video

choices. You can help them forecast streaming site. They offer content in
insurance premiums. Targeted various regional languages. Build a local
marketing using your random forest recommendation engine for Netflix
algorithm skills can help obtain better customers residing in south Bangalore
premium values. on their weekend and weekdays
activities, utilizing NLP.

Data Analytics, Matplotlib, Logical Data Analytics, Matplotlib, Logical

Regression Regression

Domain: Transportation Domain: Oil, Gas and energy

Reduction of waiting time via a Understanding in-depth about

highly precise forecasting model logging while drilling (LWD)
technique

Make a demand forecasting model Saudi Aramco company is working on

based on specific time period rider the development of high-efficiency
demands. Such a model will help both drilling models. Use the bright sides of
riders and cab drivers to ensure the big data analytics to identify the most
least possible waiting time. You can cost-effective and highly productive
include measures like latitude and drilling sites.
longitude identification.

Machine Learning, Hadoop, Time Series Matplotlib in Python, Big Data

Analysis
Real-time Projects

Domain: HR Domain: Marketing

Career progression planning of Descriptive study of trends and

employees with workforce defections irregularities with prediction analysis
& efficiency for conversion

IBM intends to boost its HR department Swiggy seeks a broad marketing

by identifying employees' masked campaign. But they need automated
inconsistency. They need models to keyword generation tools & proper
identify the graphical variations in their message preparation and delivery of the
14000+ employees' performances. Help same to the right audience at the right
them build models with your time. Help them with text analytics and
regressions and other ML abilities. NLP-based keyword research.

Machine Learning, Python, SQL, Exploratory Data Analysis, Big Data,

PySpark NLP

Domain: Sales Domain: Healthcare

Forecasting future sales with trends Understanding covid-19 cases

and price maximization and fatality rate by time series
forecasting

BMW customers can sell old vehicles, Samsung will launch a new healthcare
but rivals provide superior resale prices. app soon. The key goal of this app is an
BMW's data science-powered software accurate human activity tracking and
will deliver the greatest market value for providing relevant health-related
used vehicles based on Km travelled, recommendations. Continuous analysis
daily price changes, production dates, of a massive amount of mobile data is
etc. Such tasks build analytical abilities. required for such an app.

Scikit-learn, XG Boos, Customer Supervised Machine Learning, Python

Segmentation (Pandas Library)
 Contact Us

#1090 Book a counselling session

1st floor, 18th Cross Rd, above with expert
Sangam Sweets, Sector 3, HSR
Layout, Bengaluru, Karnataka Book Now

560102

Follow us on