deep learning

‘The Data Science & Deep Learning for BusinessTM 20 Case Studies’ course teaches how to use data science and deep learning to address real-world business problems through 20 case studies. The course is designed for individuals who are interested in data science and deep learning and want to apply these skills to solve business problems.

It is a hands-on course and includes end-to-end projects, introducing concepts as they are applied. The course covers the majority of domains that businesses typically ask about and is considered both comprehensive and unique. The courses are usually available for INR 3,499 on Udemy but you can click on the link to get 87% off and get The Data Science & Deep Learning for BusinessTM 20 Case Studies Course for INR 449.

Who all can opt for this course?

  • Aspiring data scientists
  • Business analysts who want to use their data more effectively
  • College graduates with little practical experience
  • Management or MBA students who are interested in using data to enhance their business
  • Software engineers or developers that want to begin studying data science
  • Anyone who wants to increase their employability as a data scientist

Course Highlights

Key HighlightsDetails
Registration LinkApply Now!
PriceINR 449 (INR 3,49987% off
Duration20.5 hours
Student Enrollment10,440 students
InstructorRajeev D. Ratan
Topics CoveredPython, Pandas, Statistics & Probability for Data Science, Hypothesis Testing, Machine Learning, Deep Learning
Course LevelIntermediate (familiarity with basic Programming concepts and high school maths)
Total Student Reviews960

Learning Outcomes

  • Recognize the importance of data to business
  • Solve common problems in marketing, sales, customer clustering, banking, real estate, insurance, travel, and more
  • Learn Python, Pandas, Matplotlib & Seaborn, SkLearn, NLTK, Prophet, PySpark, MLLib, and more
  • Learn machine learning using Decision Trees, Random Forests, K-NNs, Logistic Regressions, SVMs, and Polynomial and Multivariate Linear Regressions
  • Unsupervised machine learning using t-SNE, PCA, K-Means, Mean-Shift, DBSCAN, and EM using GMMs
  • Build a collaborative and item/content-based product recommendation tool
  • Understand t-tests and p values for hypothesis testing and A/B testing
  • Summarize reviews, analyze airline tweets for sentiment, and detect spam using natural language processing
  • Use AWS to deploy your machine learning models in the cloud
  • Advanced Pandas methods, including vectorization and parallel processing
  • Distributions, probability theory, statistical theory, and exploratory data analysis
  • Predicting insurance costs, Airbnb costs, credit card theft, and the recipients of gifts
  • Big Data abilities for data manipulation and machine learning with PySpark
  • Exploratory Data Analysis is used to group customers, while K-Means is used to identify client subgroups
  • Reinforcement learning is used to create a stock trading bot
  • Apply data science and analytics to the retail industry to perform segmentation, analyze trends, identify valuable clients, and more!
  • How to use data science in marketing to raise conversion rates, forecast engagement, and increase the customer lifetime value

Course Content

S.No.Module (Duration)Topics
1.Course Introduction – Why Businesses NEED Data Scientists more than ever! (01 hour 05 minutes)Introduction – Why do this course? Why Apply Data Science to Business?
Why Data is the new Oil and what most Businesses are doing wrong
Defining Business Problems for Analytic Thinking & Data Driven Decision Making
Analytic Mindset
10 Data Science Projects every Business should do!
Making Sense of Buzz Words, Data Science, Big Data, Machine & Deep Learning
How Deep Learning is Changing Everything!
The Roles in the Data World – Analyst, Engineer, Scientist, Statistician, DevOps
How Data Scientists Approach Problems
2.Course Setup & Pathways – DOWNLOAD RESOURCES HERE (05 minutes)Course Approach – Different Options for Different Students
Setup Google Colab for your iPython Notebooks (Download Course Code + Slides)
Download Code, Slides and Datasets
3.Python – A Crash Course (51 minutes)Why use Python for Data Science?
Python – Basic Variables
Python – Variables (Lists and Dictionaries)
Python – Conditional Statements
More information on elif
Python – Loops
Python – Functions
Python – Classes
4.Pandas – Beginner to Advanvced (02 hours 23 minutes)Introduction to Pandas
Pandas 1 – Data Series
Pandas 2A – DataFrames – Index, Slice, Stats, Finding Empty cells & Filtering
Pandas 2B – DataFrames – Index, Slice, Stats, Finding Empty cells & Filtering
Pandas 3A – Data Cleaning – Alter Colomns/Rows, Missing Data & String Operations
Pandas 3B – Data Cleaning – Alter Colomns/Rows, Missing Data & String Operations
Pandas 4 – Data Aggregation – GroupBy, Map, Pivot, Aggreate Functions
Pandas 5 – Feature Engineer, Lambda and Apply
Pandas 6 – Concatenating, Merging and Joinining
Pandas 7 – Time Series Data
Pandas 7 – ADVANCED Operations – Iterows, Vectorization and Numpy
Pandas 8 – ADVANCED Operations – More Map, Zip and Apply
Pandas 9 – ADVANCED Operations – Parallel Processing
Map Visualizations with Plotly – Cloropeths from Scratch – USA and World
Map Visualizations with Plotly – Heatmaps, Scatter Plots and Lines
5.Statistics & Probability for Data Scientists (01 hour 54 minutes)Introdution to Statistics
Descriptive Statistics – Why Statistical Knowledge is so Important
Descriptive Statistics 1 – Exploratory Data Analysis (EDA) & Visualizations
Descriptive Statistics 2 – Exploratory Data Analysis (EDA) & Visualizations
Sampling, Averages & Variance And How to lie and Mislead with Statistics
Sampling – Sample Sizes & Confidence Intervals – What Can You Trust?
Types of Variables – Quantitive and Qualitative
Frequency Distributions
Frequency Distributions Shapes
Analyzing Frequency Distributions – What is the Best Type of WIne? Red or White?
Mean, Mode and Median – Not as Simple As You’d Think
Variance, Standard Deviation and Bessel’s Correction
Covariance & Correlation – Do Amazon & Google know you better than anyone else?
Lying with Correlations – Divorce Rates in Maine caused by Margarine Consumption
The Normal Distribution & the Central Limit Theorem
6.Probability Theory (29 minutes)Probability – An Introduction
Estimating Probability
Addition Rule
Permutations & Combinations
Bayes Theorem
7.Hypothesis Testing (24 minutes)Hypothesis Testing Introduction
Statistical Significance
Hypothesis Testing – P Value
Hypothesis Testing – Pearson Correlation
8.Machine Learning – Regressions, Classifications and Assessing Performance (02 hours 21 minutes)Introduction to Machine Learning
How Machine Learning enables Computers to Learn
What is a Machine Learning Model?
Types of Machine Learning
Linear Regression – Introduction to Cost Functions and Gradient Descent
Linear Regressions in Python from Scratch and using Sklearn
Polynomial and Multivariate Linear Regression
Logistic Regression
Support Vector Machines (SVMs)
Decision Trees and Random Forests & the Gini Index
K-Nearest Neighbors (KNN)
Assessing Performance – Confusion Matrix, Precision and Recall
Understanding the ROC and AUC Curve
What Makes a Good Model? Regularization, Overfitting, Generalization & Outliers
Introduction to Neural Networks
Types of Deep Learning Algoritms CNNs, RNNs & LSTMs
9.Deep Learning in Detail (01 hour 34 minutes)Neural Networks Chapter Overview
Machine Learning Overview
Neural Networks Explained
Forward Propagation
Activation Functions
Training Part 1 – Loss Functions
Training Part 2 – Backpropagation and Gradient Descent
Backpropagation & Learning Rates – A Worked Example
Regularization, Overfitting, Generalization and Test Datasets
Epochs, Iterations and Batch Sizes
Measuring Performance and the Confusion Matrix
Review and Best Practices
10.Case Study 1 – Figuring Out Which Employees May Quit – Retention Analysis (40 minutes)Figuring Out Which Employees May Quit –Understanding the Problem & EDA
Data Cleaning and Preparation
Machine Learning Modeling + Deep Learning
11.Case Study 2 – Figuring Out Which Customers May Leave – Churn Analysis (31 minutes)Understanding the Problem
Exploratory Data Analysis & Visualizations
Data Preprocessing
Machine Learning Modeling + Deep Learning
12.Case Study 3 – Who Do We Target For Donations? Finding the highest incomes (28 minutes)Understanding the Problem
Exploratory Data Analysis and Visualizations
Preparing our Dataset for Machine Learning
Modeling using Grid Search for finding the best parameters
13.Case Study 4 – Predicting Insurance Premiums (22 minutes)Understanding the Problem + Exploratory Data Analysis and Visualizations
Data Preparation and Machine Learning Modeling
14.Case Study 5 – Predicting Airbnb Prices (42 minutes)Understanding the Problem + Exploratory Data Analysis and Visualizations
Machine Learning Modeling
Using our Model for Value Estimation for New Clients
15.Case Study 6 – Credit Card Fraud Detection (27 minutes)Understanding our Dataset
Exploratory Analysis
Feature Extraction
Creating and Validating Our Model
16.Case Study 7 – Analyzing Conversion Rates of Marketing Campaigns (17 minutes)Exploratory Analysis of Understanding Marketing Conversion Rates
17.Case Study 8 – Predicting Engagement – What drives ad performance? (17 minutes)Understanding the Problem + Exploratory Data Analysis and Visualizations
Data Preparation and Machine Learning Modeling
18.Case Study 9 – A/B Testing (Optimizing Ads) (39 minutes)Understanding the Problem + Exploratory Data Analysis and Visualizations
A/B Test Result Analysis
A/B Testing a Worked Real Life Example – Designing an A/B Test
Statistical Power and Significance
Analysis of A/B Test Resutls
19.Case Study 10 – Product Analytics (Exploratory Data Analysis) (31 minutes)Problem and Plan of Attack
Sales and Revenue Analysis
Analysis per Country, Repeat Customers and Items
20.Case Study 11 – Determine Your Best Customers & Customer Lifetime Values (13 minutes)Understanding the Problem + Exploratory Data Analysis and Visualizations
Customer Lifetime Value Modeling
21.Clustering – Unsupervised Learning (52 minutes)Introdution to Unsupervised Learning
K-Means Clustering
Choosing K – Elbow Method & Silhouette Analysis
K-Means in Python – Choosing K using the Elbow Method & Silhoutte Analysis
Agglomerative Hierarchical Clustering
Mean-Shift Clustering
DBSCAN (Density-Based Spatial Clustering of Applications with Noise)
DBSCAN in Python
Expectation–Maximization (EM) Clustering using Gaussian Mixture Models (GMM)
22.Dimensionality Reduction (20 minutes)Principal Component Analysis
t-Distributed Stochastic Neighbor Embedding (t-SNE)
PCA & t-SNE in Python with Visualization Comparisons
23.Case Study 12 – Customer Clustering (K-means, Hierarchial) (42 minutes)Data Exploration & Description
Simple Exploratory Data Analysis and Visualizations
Feature Engineering
K-Means Clustering of Customer Data
Cluster Analysis
24.Recommendation Systems Theory (29 minutes)Introduction to Recommendation Engines
Before recommending, how do we rate or review Items? Thought Experiment
User Collaborative Filtering and Item/Content-based Filtering
The Netflix Prize, Matrix Factorization & Deep Learning as Latent-Factor Methods
25.Case Study 13 – Build a Product Recommendation System (30 minutes)Dataset Description and Data Cleaning
Making a Customer-Item Matrix
User-User Matrix – Getting Recommended Items for each Customer
Item-Item Collaborative Filtering – Finding the Most Similar Items
26.19.1 Case Study 14 – Use LightFM to Build a Movie Recommendation System (11 seconds)Plan and Approach
27.Natural Language Processing an Introduction (20 minutes)Introduction to Natural Language Processing
Modeling Language – The Bag of Words Model
Normalization, Stop Word Removal, Lemmatizing/Stemming
TF-IDF Vectorizer (Term Frequency — Inverse Document Frequency)
Word2Vec – Efficient Estimation of Word Representations in Vector Space
28.Case Study 15 – Summarizing Amazon Reviews (10 seconds)Problem and Plan of Attack
29.Case Study 16 – Sentiment Analysis of Airline Tweets (11 seconds)Problem and Plan of Attack
30.Case Study 17 – Spam Filter (10 seconds)Problem and Plan of Attack
31.Case Study 18 – Demand Forecasting with Facebook’s Prophet (12 seconds)Problem and Plan of Attack
32.Case Study 19 – Stock Trading using Reinforcement Learning (01 minutes)Reinforcement Learning an Introduction
Using Q-Learning and Reinforcement Learning to Build a Trading Bot
33.Big Data Introduction (07 minutes)Introduction to Big Data
Challenges in Big Data
Hadoop, MapReduce and Spark
Introduction to PySpark
RDDs, Transformations, Actions, Lineage Graphs & Jobs
Simple Data Cleaning in PySpark
Machine Learning in PySpark
34.Case Study 20 – Headline Classification in PySpark (11 seconds)Using PySpark for Headline Classification
35.Data Science in Production – Deploying on the Cloud (AWS) (13 minutes)Install and Run Flask
Running Your Computer Vision Web App on Flask Locally
Running Your Computer Vision API
Setting Up An AWS Account
Setting Up Your AWS EC2 Instance & Installing Keras, TensorFlow, OpenCV & Flask
Changing your EC2 Security Group
Using FileZilla to transfer files to your EC2 Instance
Running your CV Web App on EC2
Running your CV API on EC2
36.BONUS – Customer Life Time Values using the BG/NBD and the Gamma-Gamma Model (03 minutes)Customer Lifetime Value (CLV) Theory
Buy-til-you-die (BTYD) models
Customer Lifetime Value Modeling using lifetimes
37.BONUS – Price Optimization of Airline Tickets (01 minutes)Price Optimization of Airline Tickets
38.BONUS – Convolution Neural Networks (54 minutes)Convolutional Neural Networks Chapter Overview
Convolutional Neural Networks Introduction
Convolutions & Image Features
Depth, Stride and Padding
The Fully Connected Layer
Training CNNs
Design Your Own CNN
Deep Learning Computer Vision™ CNN, OpenCV, YOLO, SSD & GANs – Promo
Deep Learning Computer Vision™ CNN, OpenCV, YOLO, SSD & GANs – Introduction

Resources Required

  • Basic Programming concepts
  • High-school level Maths
  • Stable internet connection

Featured Review

Amith reddy (5/5): Voice levels and the way the program was designed are top-notch learned a lot though I am a non-IT guy


  • Roger Lloyds (5/5): One of the best data science courses I’ve ever come across!
  • Diederik Espen (5/5): The instructor seems to have a knack for knowing what things can trip up a beginner so he explains those concepts brilliantly.
  • Arjun Achuthan (5/5): The instructor has great clarity in what he is going to teach.
  • Ben Goisima (5/5): Some of the Statistical Theory and ML theory lessons are perhaps the best on the internet! Also, I love how he relates it to business applications.


  • Mamtakakkar (2/5): Someone who has experience with case studies would know that it was poorly designed and sufficient explanation wasn’t provided.
  • Ashad (1/5): At least you need to write some of the code so that we understand.
  • Vikas Bhartiya (1/5): I do a lot of research before buying the course but this time I have trapped.
  • Karan Mehta (1/5): The instructor is not clear in his approach and does not explain things fully For example at one instance he says “cross tab is little difficult to understand” and he did not even explain it afterward.

About the Author

The instructor of this course is Rajeev D. Ratan who is a Data Scientist, Computer Vision Expert & Electrical Engineer. With a 4.4 instructor rating and 8,908 reviews on Udemy, he offers 7 courses and has taught 60,145 students so far.

  • Rajeev is a computer vision engineer and data scientist.
  • He graduated from the University of Edinburgh with a BSc in Computer & Electrical Engineering and an MSc in Artificial Intelligence, where he developed in-depth expertise in machine learning, computer vision, and intelligent robotics.
  • He even was a member of a team that won a robotics competition at the University of Edinburgh.
  • His study on employing data-driven methodologies for probabilistic stochastic modeling for public transportation has been published.
  • In order to use deep learning in education, he founded my own computer vision startup.
  • Since then, he has worked with two other companies in the computer vision space as well as a large international company in data science.
  • He previously spent eight years working for two of the biggest telecom companies in the Caribbean, where he developed skills in technical staff management and the deployment of challenging telecom projects.

Comparison Table

ParametersData Science & Deep Learning for Business™ 20 Case StudiesMachine Learning Practical: 6 Real-World ApplicationsMachine Learning Practical Workout | 8 Real-World Projects
OffersINR 455 (INR 3,499) 87% offINR 455 (INR 3,499) 87% offINR 455 (INR 3,499) 87% off
Duration20.5 hours8.5 hours14 hours
Rating4.2/54.5 /54.4 /5
Student Enrollments10,44019,61015,038
InstructorsRajeev D. RatanDr. Ryan Ahmed, Ph.D., MBADr. Ryan Ahmed, Ph.D., MBA
Register HereApply Now!Apply Now!Apply Now!

Leave feedback about this

  • Rating