What is a common method to determine the optimal number of clusters in K-means?

Practice Questions

Q1
What is a common method to determine the optimal number of clusters in K-means?
  1. Elbow method
  2. Cross-validation
  3. Grid search
  4. Random search

Questions & Step-by-Step Solutions

What is a common method to determine the optimal number of clusters in K-means?
  • Step 1: Choose a range of numbers for clusters (like 1 to 10).
  • Step 2: For each number of clusters, run the K-means algorithm.
  • Step 3: Calculate the explained variance (how well the clusters fit the data) for each number of clusters.
  • Step 4: Create a plot with the number of clusters on the x-axis and the explained variance on the y-axis.
  • Step 5: Look for the 'elbow' point in the plot where the explained variance starts to level off.
  • Step 6: The number of clusters at the elbow point is considered the optimal number.
No concepts available.
Soulshift Feedback ×

On a scale of 0–10, how likely are you to recommend The Soulshift Academy?

Not likely Very likely