Hierarchical Clustering is an important term in the fields of Big Data and Smart Data, as well as Artificial Intelligence. It is a method by which large amounts of data can be sensibly grouped. The aim of Hierarchical Clustering is to combine similar data points into groups, known as clusters.
Imagine you have thousands of customer data points and want to find out which customers exhibit similar behaviour. With Hierarchical Clustering, a computer program first identifies the most similar customers and groups them together. It then merges the second most similar groups, and so on, until all the data is organised into a large hierarchy of clusters – much like a branching family tree.
This results in a clear structure in which each element belongs to a specific cluster. Companies use this, for example, to better understand their target groups and create individual offers.
A clear example: An online shop wants to analyse its product reviews. Hierarchical Clustering automatically recognises similar review texts and groups them. This way, the shop can immediately see which products are often praised for their high quality and which frequently receive similar criticisms. This saves time and helps with better business decisions.
Deutsch 
English (UK)