Using an objective function that minimizes the within-cluster sum of squares (WCSS) causes K-Means to produce spherically shaped clusters. If it makes sense to find globular clusters within the data, K-Means performs quite well and is an appropriate way to cluster it; however, if it makes more sense to find elliptical clusters or irregularly-shaped clusters in higher-dimensional space, K-Means is usually not the best choice.
What is the effect of minimizing the within-cluster sum of squares on the shapes of clusters produced in K-Means?
Using an objective function that minimizes the within-cluster sum of squares (WCSS) causes K-Means to produce spherically shaped clusters. If it makes sense to find globular clusters within the data, K-Means performs quite well and is an appropriate way to cluster it; however, if it makes more sense to find elliptical clusters or irregularly-shaped clusters in higher-dimensional space, K-Means is usually not the best choice.
Help us improve this post by suggesting in comments below:
– modifications to the text, and infographics
– video resources that offer clear explanations for this question
– code snippets and case studies relevant to this concept
– online blogs, and research publications that are a “must read” on this topic
Partner Ad