As seen in the previous blog posts in this article serie (the first blog post in the serie was Understanding AI Algorithms), we can classify data into defined groups in a number of ways.
However, what if we don’t know a lot about our data?
This is where clustering algorithms step in. A cluster is simply a group of observations that are close together based on some similarity, be it physical distance or another measure.
For example, in a restaurant, each table could be said to be clusters of guests.
These algorithms are used to put observations into groups that we did not know existed. Hence, clustering algorithms are about group associations.
For example, if we are trying to get to know our customers that visit our company’s website, a clustering algorithm could be used to group them and allow us to examine the different groups. We can then understand which customers are alike, how they differ, and what their characteristics are.
In the sub-pages of this blog post, we will become familiar with three algorithms that approach clustering problems in different ways. Each is useful when analyzing how pieces of data are related and to help understand those relationships:
If you want to read all the related articles on the topic of AI algorithms, here is the list of all blog posts in this article series:
