As clumsy as I am, I have lost count of the books I read, I believe I am between the seventh and eighth at the time I am writing this publication, but I am happy to have finished one of the books that may be the most painful on the head this year, I'm talking about the
Data Science for Business Tom Fawcet's book, which although I liked much of the experience of having read this book was not as much fun as I thought it would be.
1. Putting the pieces together
Well, before my analysis makes you change your mind about getting this book or not, I'll say for my experience as a programmer,, this one book was worth buying.
"Success in today's business environment, requires the ability to think about how these fundamental concepts apply to certain business problems - think analytically in data ".
- Data Science for Business
Like other people I've heard of this book, I've understood it to be great for managers, directors, or leaders who need to understand how to evaluate a Data Science professional and how to hire them. You end the book by understanding how various Data Science concepts work, and at the same time you apply them to those who already work in that area, the book may present some Insights interesting.
2. The other hand
However, as the book itself says, it's not a technical book, not that it's a problem, on the contrary, maybe that's the best thing about this book. What might have given me some discomfort to read it, was that the book is not as educational as I thought it would be.
The examples presented in this book are great, they are based on real events and it goes very well to explain them, but perhaps the lack of visualizations and metaphors made me have to think hard about what I was reading. there are other books that are very good at bringing the reader with metaphors, such as Understanding Algorithms by Aditya Y. Bhargava.
Perhaps this has happened to me, because Machine Learning and Data Science are not at all trivial matters, which require a certain commitment from any professional who wishes to learn about it. It is possible that with other books that have a more didactic proposal make me understand and enjoy the book much more. Or it has been a loss of my expectation.
Another problem of this book is perhaps the size, not that it could be different, after all it has a fair size to explain so many concepts, though I believe that if he separated the book into 3 parts, explaining to the reader that he should perfectly understand each part to go on, it would feel better when I was reading.
3. In the end, all be alright
I was pleased to finish this book, it took me a long time but it was not a complete waste, unfortunately I may have to revise it when it is more used to the Data Science universe. The good thing about this book is that for an already savvy professional, it's objective and accurate in all its applications, so a statistician or a more experienced programmer with this area of data analysis will probably love this approach.
My recommendation: If you are new to the area of statistics and Big Data, I suggest you read only the chapters pertaining to the work of Data Science, then read other more didactic books on mathematics for Data Science and after much practice re-read it. If you start with this book, there's a good chance you'll get frustrated. Keep this book fondly, but speaking of analogy, treat this book as the Nemesis of RE3, you will have to face it several times, but only after a while will you be ready to defeat it.