A medoid is a data point that serves as the representative of a cluster in clustering algorithms, particularly in the context of partitioning methods like K-means. Unlike the centroid, which is the average of all points in a cluster, the medoid is the most centrally located point within that cluster, minimizing the sum of dissimilarities to all other points. This property makes medoids robust to outliers, as they are actual data points rather than calculated averages.
congrats on reading the definition of Medoid. now let's actually learn it.