Data Analysis

Businesses sit on data, and every second that passes, they generate some more. Surely, there must be a way to make use of all this stuff. But how, exactly—that’s far from clear.

The task is difficult because it is so vague: there is no specific problem that needs to be solved. There is no specific question that needs to be answered. All you know is the overall purpose: improve the business. And all you have is “the data.” Where do you start?

You start with the only thing you have: “the data.” What is it? We don’t know! Although 50 GB sure sounds like a lot, we have no idea what it actually contains. The first thing, therefore, is to take a look.

And I mean this literally: the first thing to do is to look at the data by plotting it in different ways and looking at graphs. Looking at data, you will notice things—the way data points are distributed, or the manner in which one quantity varies with another, or the large number of outliers, or the total absence of them.... I don’t know what you will find, but there is no doubt: if you look at data, you will observe things!