Have you ever thought that there is a difference between such terms as “data”, “information” and “knowledge”? Often people mix and misuse them and it’s not a problem in our daily life, but when we come to Data Mining it’s good to distinguish them. Here I’ll try to show the difference in an comprehensible way.


Simply speaking, data is everything that is given to us. It’s a kind of raw material. The whole world is full of different kinds of things (whether useful or not), and almost all these things can be  converted into digital form and described in numbers (probably you are familiar with this).

A set of Hebrew characters represents some data: ב ו א ה ר ב ך


When data represents something definite, we may call it  information. In other words, when uncertainty (in information theory the degree of uncertainty is called entropy) is decreased,  more information appears. For example, where do we have more information? In a set of random digits or in Fibonacci numbers? Of course, in the second case.

A Hebrew word gives some information: ברוך הבא


When information is applied it is knowledge. When you understand information and apply it to make a decision, it becomes knowledge. For example, if you have a text in a foreign language,  it gives some information, but unless you translate it, you can not get any knowledge out of it.

A translated Hebrew word gives you knowledge: welcome