This is one of those books that explain difficult concepts using plain language. It helps the reader completely understand the complex topics by starting from the basics. It is a must-read book for anyone who wants to know how the future will look. The future is data, billions of data. So, how can we take advantage of this immense amount of data?
As this work clearly states, data science comprises two broad areas, statistics and machine learning. The first area aims at explaining and displaying data in an understandable and friendly way to users, that is, human beings. The second area deals with finding patterns and relations between the data in order to train machines to foresee what can happen in the near or far future (the further into the future, the more uncertain).
In addition to its excellent attention to detail and pedagogic style, the book also has plenty of technical facts, for example, the importance of selecting the right attributes or using the proper correlations for getting the most meaningful information. Traditional database principles versus modern database (Hadoop) principles are also addressed. Machine learning receives a comprehensive review, and the book also highlights the key aspects of state-of-the-art deep neural nets.
The book closes with three excellent chapters: some study cases, ethics and privacy, and future trends. The glossary at the end is very much appreciated.
More reviews about this item: Amazon, Goodreads