Which of the following is NOT a characteristic of K-means clustering?
Practice Questions
Q1
Which of the following is NOT a characteristic of K-means clustering?
It can converge to local minima
It can handle non-spherical clusters well
It is sensitive to the initial placement of centroids
It requires numerical input data
Questions & Step-by-Step Solutions
Which of the following is NOT a characteristic of K-means clustering?
Step 1: Understand what K-means clustering is. It is a method used to group data points into clusters based on their similarities.
Step 2: Know that K-means clustering assumes that the clusters are spherical in shape. This means it expects the clusters to look like balls.
Step 3: Realize that K-means also assumes that all clusters are of similar size. This means it thinks each group of data points has about the same number of points.
Step 4: Identify that if the actual data has clusters that are not spherical or are of different sizes, K-means will not perform well.
Step 5: Conclude that the characteristic of struggling with non-spherical clusters is NOT a feature of K-means clustering, but rather a limitation.
