Comments about oreilly Data Science for Business:

Loved this book. Well written, easy to understand.

Comments about oreilly Data Science for Business:

liked the introduction to text mining especially through stemming, ngrams ...

Comments about oreilly Data Science for Business:

A very well written book by very experienced educators that are also excellent scientists.
The non-mathematical approach taken by the authors is remarkable.

Comments about oreilly Data Science for Business:

Having gone to school just before "data science" became a widespread thing, I had training in a variety of "quantitative analysis" techniques but not the field of "data analytics."

I professionally used simulation models and statistical analysis as a consultant, and was well aware of the growing technique library in the "data analysis" field, but generally still referred to myelf as a "quant" (quantitative analyst).

This book served as an excellent way to tie my peripheral knowledge of different techniques and the "jargon" of data analytics in to a coherent whole. Although I was familiar with many of the terms and techniques, I'm much more confident in my ability to select, describe, and justify individual analytic techniques in a project context now.

I recommend this text to anybody who comes in to contact with data analytics. In particular, the discussions of how and why to select particular models, and the pitfalls of analysis like overfitting, are excellent material for a wide variety of business positions, as are the appendices challenging the reader to evaluate data analytics proposals.

Comments about oreilly Data Science for Business:

I carry this book with me all the time, and I read it any time I have a spare moment. I am a CTO in a data analytics company and I find myself frequently in the need of explaining how and where data analytics can help businesses.
I also find the need to inspire myself with some interesting applications that I did not have chance to try out yet. This book gives me both.
The book has a rare computational, mathematical, and business depth that will satisfy both a computer scientist and a business person with a curious mind.

Comments about oreilly Data Science for Business:

I came across this book when preparing to interview for a sales position at a marketing technology company whose product relies on collecting, interpreting and making data actionable. It took less than a couple of hours to find myself immersed in real, recognizable stories, set as examples of data science's ability to reimagine the synthesis of a problem and present a hidden-from-plain-sight answer. Shortly afterward, I was introduced to the fundamental principles of data science, which expanded my analytical thinking, giving it multidimensionality and an understanding of how to expose a problem's solution, whether in business, the arts, social science, or life itself.

In a world where an ever-increasing amount of actions and interactions are collected and stored in readily available data sets, those who master the analytical thinking to mine them will attain a significant competitive advantage.

Comments about oreilly Data Science for Business:

The future of computers is with data. But what do you need to know. This is a great overview of the field.

It is perfect for helping a business person understand the terminology and processes involved in machine learning, statistical analysis, data mining, and the general data driven business plan.

This book is also perfect for someone interested in computer science, but needing the complexities placed into some form of organization that will better help them decide what they want to focus on (or in what order).

LEVEL: Beginner - Intermediate computer science OR ANY LEVEL Business Professional.

In short, I believe that this is one of the core fields that everyone should have knowledge about, and this book does a great job of covering what data science is and how it is used.

Comments about oreilly Data Science for Business:

I had high expectations for this book. It's a part of the data science toolkit offered by O'Reilly and I own a majority of those books in that kit. I was disappointed at the 1.) scope of the book, 2.) depth of the book and 3.) applications towards business.

Scope: I've read the Programming Collective Intelligence book, Machine Learning for Hackers and a few others so I'm aware of the breadth of topics the authors could have chosen. However, their supervised and unsupervised methods were really limited to: classification problems (Decision Trees, Clustering), Expected Value (very useful) and model evaluation. They only mention linear regression in passing. Maybe they considered it too basic, but I have to imagine predicting a value is more frequently done than classification problems.

Depth: With the narrow focus they did explain the concepts of k-Nearest Neighbors, Decision Trees, and Expected value VERY well but there's no code and the bibliography is not sorted by chapters so it's harder to identify where you should go next. Had the authors at least done pseudo-code I would have appreciated the effort. It would still have been appropriate for managers who need to know the basics of these advanced analytical techniques.

Business: This peeved me the most. There were only two real "applications" / examples used that were related towards business - Churn of wireless phone customers and targeted advertising. I feel like the "for business" portion of the title set the expectation too high.

However, if you need to get a general understanding of decision trees, clustering and "expected value" of targeted advertisements, this is a good book. I can definitely see a person with zero analytics experience but having to manage a team of advanced analysts would definitely benefit from this book - little math but great explanations (for the topics that are discussed). In addition, I could see this book as being supplemental to a high-level database marketing class (i.e. one that doesn't go into the math of the algorithms but just runs the procedures and interprets the results).

Bottom Line: Not deep enough to start doing the analyses and not enough examples of real business applications to generate many new ideas for your own work.

Comments about oreilly Data Science for Business:

"Data Science for Business" is extremely well written for data scientists. It identifies a small set of fundamental principles underlying data science. By walking you through these fundamentals, you can easily understand many well-known data mining algorithms. A broad set of practical data analytic skills based on real world applications introduced can help you perform data analytics effectively. Overall, it is broad, deep, but not too technical. Readers do not need sophisticated mathematics and statistics background to understand the concepts and methodologies in data science.

Comments about oreilly Data Science for Business:

It's a great textbook that clearly tells the underlaying concepts of data analysis approaches, without making you scared or feel incapable.

Only the basic equations are given if they're really necessary throughout the book, which makes you comfortable reading the book. Also this helps you to read the book uninterrupted, which also keeps you motivated during the chapters. I wanted to learn the fundamental concepts many times from different sources (books, tutorials, MOOCs) but this book is the best among them. I actually use many of the approaches mentioned in the book but after finishing the book that I feel that I've really understood and digested the concepts.

I've already started to suggest this book to my friends and colleagues, and strongly recommend for anyone interested in learning the background of data analysis approaches.