Which method is commonly used to determine the optimal number of clusters k in k-Means by plotting WCSS against k?
The Elbow Method plots WCSS vs k and identifies the 'elbow' point where the rate of decrease abruptly slows.
How does k-Medoids (PAM) clustering differ from standard k-Means clustering?
k-Medoids selects actual data points (medoids) as cluster representatives, making it robust to noise and outliers compared to mean-based k-Means.
Which density-based clustering algorithm can discover clusters of arbitrary shapes and identify noise/outliers?
DBSCAN clusters data based on density (eps and minPts), effectively discovering arbitrary shapes and identifying noise points.
In DBSCAN, a point is classified as a CORE POINT if:
A point p is a core point if |$N_{eps}$(p)| >= minPts.
In DBSCAN, what is a BORDER POINT?
Border points are within eps of a core point but do not have minPts neighbors themselves.