I have a cluster with many points.
Like this:
Where I can visually identify a cluster of points and a noise point.
Question: I would like to know how can I find the best fit point via an algorithm/math formulas. Not the centroid of the cluster, but the best fit point... probably the closest point to the cluster centroid without taking into account the noise point(s).
The PAM algorithm (for partition around medoïd) is an algorithm close to the usual k-means which allows to works with data points as cluster centers.