Book Review: Numbersense

Author: Kaiser Fung

Publisher: Mcgraw Hill Education

MyRating: 4/5

‘Numbersense: How to Use Big Data to Your Advantage’ is not such type of book that we often grab to read. Especially when the book is published by Mcgraw Hill Education, that reminds us of our old college days, make even more difficult to hold the book. When we were told that we are born with five senses (seeing, hearing, touch, taste and smelling) and suddenly somebody says about the other sense (number sense), it is difficult to ignore the author’s intention.

Kaiser Fung, who is a professor at New York University teaches practical statistics, is the author of this book who also wrote ‘Numbers Rule the World’. He claims that Numbersense gives you the insight how big data interpretations works and how it too often doesn’t work.

Numbersense is not another book of statistics or data analysis that tell about how to manage, represent and analyze data but it shows, using many examples, how to develop the sense to recognize ‘misleading behaviour’ of big data. Number sense is the noise in your head when you see big data or bad analysis. It is the desire and persistence to get close to the truth.

The book is divided into four sections; social data, marketing data, economic data and sporting data. In these four sections author has shown that how the data has been used to manipulate the results in the society.

Measuring anything subjective like; aptitude of students, quality of teacher, employee performance etc always carries a pinch of doubt as they don’t carry intrinsic value. How much amount of fat in the body can be find out using several diagnostic methods but how obese a person is a matter of perception supporting by specific measuring tool. As shown in the book, the percentage of obese population gets change when DXA (Dual-energy X-ray absorptiometry) is used in place of BMI (Body-Mass Index).

The most elaborative and interesting section is ‘marketing data’ section which unveils the strategies and business model of Groupon, an online business that sells deals. One set of data favours Groupon in benefiting the local merchants whereas another set of data claims that Groupon is hurting the business of local merchants. When such confusion arises then there comes number sense which differentiates the objectives of data. Another element of Groupon under study in the book is ‘Target market’. Groupon communicates with its clients through Emails, which they send to their target market. The success rate of their targeting model is 0.06% ie for every 10000 emails they get deals from 6 clients. Many targeting strategies are recommended on the basis of different sets of data.

The author raises questions on how economic data is far away from the truth. The inflation and employment data are adjusted using the adjustment factor and assumptions which make it hard-to-believe for any data analyst. In the epilogue of this book, the author expects from the readers that they won’t take data at its face value ever again and they look it under the hood.

In all the sections of the book the author comprehensively explained with examples that what is shown is not always true. The examples are quite apt with the topics and easily understood as they are explained in simple language without using the statistical jargons. It’s a good-read for those who are interested in behind-the-scene-theories and like to crunch numbers to find out the truth. But obviously it’s not a casual read.