This module will discuss the process and value of clustering data in Qlik Sense. Clustering is a mathematical method for grouping data based upon similarities across multiple measures. The k-means clustering algorithm is applied in order
to accomplish clustering based upon two measures (2D clustering) or more than two measures. In addition, the potential need to normalize data, and the option to determine the number of cluster groups relative to the degree of similarity of items
grouped are discussed in this module.
Learning Objectives:
- Use the Insight Advisor to generate and manipulate k-means clustering results
- Consider the impact of normalization techniques on k-means clustering results
- Deconstruct and understand the k-means clustering expression
- Compare the KMeans2D() clustering function to the KMeansND() clustering function
- Understand how to interact to adjust to interpret k-means clustering results
Content last reviewed and updated on 13-Nov-2023