-->
Navigation
Machine Learning Applications Using Python: Cases Studies from Healthcare, Retail, and Finance

Machine Learning Applications Using Python: Cases Studies from Healthcare, Retail, and Finance

Now pay Easier and Secure using Paypal
Price:

Read more

Puneet Mathur


E-BOOKS SHOP
E-BOOKS SHOP
Purchase Now !
Just with Paypal



Book Details
 Price
 3.00 USD
 Pages
 384 p
 File Size
 7,104 KB
 File Type
 PDF format
 ISBN-13 (pbk) 
 ISBN-13 (electronic) 
 978-1-4842-3786-1
 978-1-4842-3787-8
 Copyright   
 2019 by Puneet Mathur  

About the Author
Puneet Mathur Advisory Board Member & Senior Machine
Learning Consultant. Puneet is an experienced hands-on
machine learning consultant working for clients from large
corporations to startups and on multiple projects involving
machine learning in healthcare, retail, finance, publishing,
airlines, and other domains. He is an IIM Bangalore alumni
of BAI and Machine Learning Engineer Nanodegree
Graduate from Udacity. He is also an open source Python
library volunteer and contributor for machine learning
scikit-learn. For the past 6 years, he has been working as a Machine Learning Consultant
for clients around the globe, by guiding and mentoring client teams stuck with machine
learning problems. He also conducts leadership and motivational workshops and
machine learning hands-on workshops. He is an author of nine self-published books
and his new two-volume book series, The Predictive Program Manager based on Data
Science and Machine Learning, is his latest work. He is currently writing books on
Artificial Intelligence, Robotics, and Machine Learning. You can learn more about him

About the Technical Reviewer
Manohar Swamynathan is a data science practitioner and
an avid programmer, with over 14+ years of experience
in various data science-related areas including data
warehousing, Business Intelligence (BI), analytical tool
development, ad-hoc analysis, predictive modeling, data
science product development, consulting, formulating
strategy, and executing analytics program. He’s had a career
covering life cycles of data across different domains such
as US mortgage banking, retail/e-commerce, insurance,
and industrial IoT. He has a bachelor’s degree with a
specialization in physics, mathematics, and computers and a master’s degree in project
management. He’s currently living in Bengaluru, the Silicon Valley of India.
He has authored the book Mastering Machine Learning With Python - In Six Steps
and been involved in technical review of books around Python & R. You can learn more
about his various other activities on his site http://www.mswamynathan.com.

Introduction
The idea of writing this book came up when I was planning a machine learning
workshop in Bangalore in 2016. When I interacted with people, I found out that although
many said they knew machine learning and had mostly learned it through self-study
mode, they were not able to answer interviewers’ questions on applying machine
learning to practical business problems. Even some of the experienced machine
learning professionals said they had implementation experience of computer vision
in a particular area like manufacturing; however, they did not have the experiential
knowledge on how it can be applied in other domains.

As of the writing of this book, the three most progressive and promising areas for
implementation are healthcare, retail, and finance. I call them promising because there
are some applications that have been built in areas like healthcare (e.g., with expert
robotic processes like surgical operations); however, there are more applications that
are being discovered every day. Retail affects everyday lives of everybody on this planet,
as you need to shop for your personal needs. Whether you buy from a grocery store or
a retail chain, online machine learning and artificial intelligence is going to change the
customer experience by predicting their needs and making sure the right solutions are
available at the right time. Finance is another area that holds a lot of promise and has
seen less application of machine learning and artificial intelligence in comparison to the
other sectors. The primary reason for that is because it is the sector with the maximum
regulations and law enforcement taking place heavily here. It is also the sector which forms
the backbone of the economy. Without finance, there is no other sector that can operate.

Readers, be they those who are just starting off with machine learning or with
experience in Python and machine learning implementation in projects other than these
sectors, will definitely gain an experiential knowledge that I share with you the through
the case studies presented in this book. The reader will get motivation from my famous
quote on artificial intelligence and machine learning it is not the Artificial Intelligence
but the Human Intelligence behind the Artificial Intelligence that is going to change the
way we live our lives in the future.

There are three sections in this book, and I think each of these could have been
printed as separate books in themselves. The good thing that the reader will find is
that the structure of these three sections is identical. Each section starts off with an
overview section where you will understand the current scenarios for that segment,
such as healthcare, retail, or finance. Then there is the technological advancement
chapter common to all the three segments, where the state of machine learning has been
discussed in detail. It is also the section where I present to you the results of the Delphi
Method expert survey for each of those domains. Then there is a chapter on how to
implement machine learning in that particular domain. This is where you will learn how
to use an industry-emulated or modeled data set and how to implement it using Python
code, step-by-step. Some of this code and approach you will be able to directly apply
in your project implementations. In each section, you will find two case studies taken
from practical business problems, again modeled on some of the practical business
problems that are commonly faced by businesses in that industry segment. Each case
study is unique and has its own questions that you must carefully study and try to
answer independently. I have given the solution for only one of the case studies using
Python code, and I have let the second case study in each section be a discussion-only
solution. The reason for doing this is because I want you to apply your own mind to solve
them after looking at how I have solved the first one. Please remember each business
is different, and each solution has to also be different. However, the machine learning
approach does not differ much.

Table of Contents
About the Author ..................................................................................................... xi
About the Technical Reviewer ............................................................................... xiii
Acknowledgments ...................................................................................................xv
Introduction ...........................................................................................................xvii
Chapter 1: Overview of Machine Learning in Healthcare
Installing Python for the Exercises ................................................................................................ 2
Process of Technology Adoption .............................................................................................. 2
How Machine Learning Is Transforming Healthcare ................................................................ 8
End Notes .................................................................................................................................... 11
Chapter 2: Key Technological advancements in Healthcare 
Scenario 2025 ............................................................................................................................. 13
Narrow vs. Broad Machine Learning ........................................................................................... 14
Current State of Healthcare Institutions Around the World ......................................................... 16
Importance of Machine Learning in Healthcare .................................................................... 19
End Notes .................................................................................................................................... 34
Chapter 3: How to Implement Machine Learning in Healthcare
Areas of Healthcare Research Where There is Huge Potential .................................................... 37
Common Machine Learning Applications in Radiology ............................................................... 40
Working with a Healthcare Data Set ........................................................................................... 41
Life Cycle of Machine Learning Development ....................................................................... 41
Implementing a Patient Electronic Health Record Data Set ........................................................ 44
Detecting Outliers .................................................................................................................. 52
Data Preparation .................................................................................................................... 67
End Notes .................................................................................................................................... 75
Chapter 4: Case Studies in Healthcare AI
CASE STUDY 1: Lab Coordinator Problem ................................................................................... 78
CASE STUDY 2: Hospital Food Wastage Problem ...................................................................... 100
Chapter 5: Pitfalls to Avoid with Machine Learning in Healthcare
Meeting the Business Objectives .............................................................................................. 122
This is Not a Competition, It is Applied Business! ..................................................................... 123
Don’t Get Caught in the Planning and Design Flaws ................................................................. 126
Choosing the Best Algorithm for Your Prediction Model ........................................................... 129
Are You Using Agile Machine Learning? .................................................................................... 130
Ascertaining Technical Risks in the Project .............................................................................. 131
End Note ................................................................................................................................... 134
Chapter 6: Monetizing Healthcare Machine Learning
Intro-Hospital Communication Apps ......................................................................................... 135
Connected Patient Data Networks ............................................................................................ 140
IoT in Healthcare ....................................................................................................................... 142
End Note ................................................................................................................................... 145
Chapter 7: Overview of Machine Learning in Retail
Retail Segments ........................................................................................................................ 149
Retail Value Proposition ............................................................................................................ 151
The Process of Technology Adoption in the Retail Sector ......................................................... 153
The Current State of Analytics in the Retail Sector ................................................................... 155
Chapter 8: Key Technological Advancements in Retail 
Scenario 2025 ........................................................................................................................... 159
Narrow vs Broad Machine Learning in Retail ............................................................................ 161
The Current State of Retail Institutions Around the World ......................................................... 162
Importance of Machine Learning in Retail ................................................................................ 164
Research Design Overview: ...................................................................................................... 170
Data Collection Methods ........................................................................................................... 170
Data Analysis ............................................................................................................................ 171
Ethical Considerations .............................................................................................................. 171
Limitations of the Study ............................................................................................................ 171
Examining the Study ................................................................................................................. 172
Phases of Technology Adoption in Retail, 2018 ................................................................... 179
End Notes .................................................................................................................................. 181
Chapter 9: How to Implement Machine Learning in Retail
Implementing Machine Learning Life Cycle in Retail ................................................................ 185
Unsupervised Learning ........................................................................................................ 186
Visualization and Plotting .................................................................................................... 190
Loading the Data Set ........................................................................................................... 193
Visualizing the Sample Data Set .......................................................................................... 198
Feature Engineering and Selection ..................................................................................... 201
Visualizing the Feature Relationships .................................................................................. 204
Sample Transformation ....................................................................................................... 206
Outlier Detection and Filtering ............................................................................................. 207
Principal Component Analysis ............................................................................................. 210
Clustering and Biplot Visualization Implementation ............................................................ 212
End Notes .................................................................................................................................. 216
Chapter 10: Case Studies in Retail AI
What Are Recommender Systems? ........................................................................................... 217
CASE STUDY 1: Recommendation Engine Creation for Online Retail Mart ................................ 218
CASE STUDY 2: Talking Bots for AMDAP Retail Group ............................................................... 233
End Notes .................................................................................................................................. 237
Chapter 11: Pitfalls to Avoid With Machine Learning in Retail
Supply Chain Management and Logistics ................................................................................. 239
Inventory Management ............................................................................................................. 241
Customer Management ............................................................................................................. 242
Internet of Things ...................................................................................................................... 245
End Note ................................................................................................................................... 247
Chapter 12: Monetizing Retail Machine Learning
Connected Retail Stores ............................................................................................................ 249
Connected Warehouses ............................................................................................................. 252
Collaborative Community Mobile Stores ................................................................................... 254
End Notes .................................................................................................................................. 257
Chapter 13: Overview of Machine Learning in Finance 
Financial Segments .................................................................................................................. 261
Finance Value Proposition ......................................................................................................... 262
The Process of Technology Adoption in the Finance Sector ...................................................... 265
End Notes .................................................................................................................................. 270
Chapter 14: Key Technological Advancements in Finance
Scenario 2027 ........................................................................................................................... 271
Narrow vs Broad Machine Learning in Finance ........................................................................ 272
The Current State of Finance Institutions Around the World ..................................................... 274
Importance of Machine Learning in Finance ............................................................................. 274
Research Design Overview ....................................................................................................... 280
Data Collection Methods ........................................................................................................... 281
Data Analysis ............................................................................................................................ 281
Ethical Considerations .............................................................................................................. 282
Limitations of the Study ............................................................................................................ 282
Examining the Study ................................................................................................................. 282
Phases of Technology Adoption in Finance, 2018 .................................................................... 290
End Notes .................................................................................................................................. 292
Chapter 15: How to Implement Machine Learning in Finance
Implementing Machine Learning Life Cycle in Finance ............................................................ 297
Starting the Code ................................................................................................................. 299
Feature Importance ............................................................................................................. 304
Looking at the Outliers ........................................................................................................ 306
Preparing the Data Set ........................................................................................................ 309
Encoding Columns ............................................................................................................... 312
Splitting the Data into Features ........................................................................................... 313
Evaluating Model Performance ........................................................................................... 313
Determining Features .......................................................................................................... 321
The Final Parameters .......................................................................................................... 324
End Note ................................................................................................................................... 324
Chapter 16: Case Studies in Finance AI
CASE STUDY 1: Stock Market Movement Prediction ................................................................. 325
Questions for the Case Study .............................................................................................. 327
Proposed Solution for the Case Study ................................................................................. 328
CASE STUDY 2: Detecting Financial Statements Fraud ............................................................. 347
Questions for the Case Study .............................................................................................. 349
Discussion on Solution to the Case Study: .......................................................................... 349
End Notes .................................................................................................................................. 354
Chapter 17: Pitfalls to Avoid with Machine Learning in Finance 
The Regulatory Pitfall ................................................................................................................ 355
Government Laws and an Administrative Controller, the Securities and
Trade Commission (SEC) ...................................................................................................... 358
States Laws and Controllers ................................................................................................ 358
Self-Regulatory Organization .............................................................................................. 359
The Data Privacy Pitfall ............................................................................................................. 360
End Note ................................................................................................................................... 362
Chapter 18: Monetizing Finance Machine Learning
Connected Bank ........................................................................................................................ 363
Fly-In Financial Markets ........................................................................................................... 367
Financial Asset Exchange ......................................................................................................... 369
End Note ................................................................................................................................... 372
Index ..................................................................................................................... 373


Bookscreen
E-BOOKS SHOP

I know for sure that many of you who read this book are highly experienced machine
learning professionals in your field and that is why you are looking for expert advice on
how to avoid common gotchas or pitfalls during machine learning in that domain, such
as healthcare or retail or finance. Each sector has its own set of pitfalls, as the nature of
the business is very different.

There could be many readers who could belong to the startup eco-system and would
like to get new ideas on implementation of machine learning and artificial intelligence
in these areas. In each of the three sections, you will find three innovative ideas that I
present to you that you could immediately take and start implementing.
If you are looking for a book that gives you experiential and practical knowledge of
how to use Python and solve some of the problems in the real world, then you will be
highly satisfied.

All the Python code and the data sets in the book are available on my website URL:
http://www.PuneetMathur.me/Book009/. You will need to register there using your
e-mail ID and the link to download the code, and data sets will be sent to you as part of
the registration process.

0