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

by Puneet Mathur

Part 1 : HealthcareChapter 1. Overview of machine learning in healthcare.Chapter 2. Key technological advancements in healthcare.Chapter 3. How to implement machine learning in healthcare.Chapter 4. Case studies on how organizations are changing the game in the market.Chapter 5. Pitfalls to avoid while implementing machine learning in healthcare.Chapter 6. Healthcare specific innovative Ideas for monetizing machine learning.Part 2: Retail Chapter 7. Overview of machine learning in Retail.Chapter 8. Key technological advancements in Retail.Chapter 9. How to implement machine learning in Retail.Chapter 10. Case studies on how organizations are changing the game in the market. c. One discussion based case study. d. One practical case study with Python code.Chapter 11. Pitfalls to avoid while implementing machine learning in retail.Chapter 12. Retail specific innovative Ideas for monetizing machine learning.Part 3: Finance Chapter 13. Overview of machine learning in Finance.Chapter 14. Key technological advancements in Finance.Chapter 15. How to implement machine learning in Finance.Chapter 16. Case studies on how organizations are changing the game in the market. e. One discussion based case study. f. One practical case study with Python code.Chapter 17. Pitfalls to avoid while implementing machine learning in Finance.Chapter 18. Finance specific innovative Ideas for monetizing machine learning.

Paperback

Published January 1, 2019

Reviews

[alex · Rating 2 out of 5]

This book has some useful information but over half of it it’s just to be there. Pages with nothing useful, or should I say, a waste of time.
The information should be kept in a compact form. I think I saw this part “I have removed the names deliberately to maintain confidentiality” for over 20 times in this book. How would I say this: we don’t care, just get to the point. As I said, it’s like this book was made to waste the time of the reader. Very little useful info for over 300 pages. If someone would rewrite this book, should be around 100-150 pages and just useful things, not repeating the same story on every 30 pages.

[Islomjon · Rating 3 out of 5]

Actually, I was not expecting panacea for ML pipelines by reading this book. However, being massive 384 pages are spent for problem definitions that are loosely related to ML industry. The book as if written from conference speeches frim different topics, author has a very little knowledge how to write technical books with precise concepts. It has a lot of typos, meanigless explanations and, how author claims, ideas for monetizing ML, but without ML entirely.

In contrast, Puneed Mathur did a good job in analyzing datasets giving the key insights where to pay attention and draw conclusions. Anyway, even the statistical analysis was in the degree of school student who tries to explain unnecessary and obvious things just to fill pages with words.