Back to GalleryK-Medoids (PAM)
K-Medoids is a clustering algorithm related to K-Means, but with one key difference: it chooses actual data points (medoids) as cluster centers rather than arbitrary coordinates (centroids). This makes it far more robust to noise and extreme outliers.
Key Parameters & Visual Influence:
• K (Clusters): The number of target clusters. The cluster boundaries will adjust around actual members of the dataset.
• Distance Metric: Supports Euclidean and Manhattan distance, changing the shape of the cluster partitions from circular to diamond-like.
Dataset Studio
CSV format: Headers in first row, last column = label/target. All values must be numeric.
Example: x1, x2, label