Cluster analyses are very flexible in terms of tasks they can perform; therefore, it has been proved to be useful in many different situations. To cite some utilities, clusters can be used to build recommenders, extract important features from data that can be used to drive insights, or further feed other models and land predictions.
This section aims to go beyond Chapter 4, KDD, Data Mining, and Text Mining. The goal here is to deepen the discussion about clusters while trying to retrieve important features from the car::Chile dataset using different techniques. Expect to see hierarchical, k-means and fuzzy clusters in this section.
All of the clusters have a huge thing in common; they are all unsupervised learning techniques. Unsupervised means that models won't target a variable during the training; there is no such thing as the dependent...
