I've been working on a clustering project where I cluster customers based on their thresholds.    For example   Distance from centroid:        Avg TH for Cluster:          Target:      0.0617                                       8977                                     8000     The goal of this project is to be able to predict thresholds for a customers based on their cluster average threshold and the distance from that cluster's centroid.   For the above example, when scaled the values would look like:   Distance from centroid:        Avg TH for Cluster:          Target:      0.89                                           8977                                     8000   (0.89) * 8977 = 8000   However, there is an obvious scaling issue between the distance from centroid values and the average threshold per cluster value.  I've explored Proc Transgres and OPSCAL, however I am not sure how I can incorporate the multiplication of the two values to get the target value. ... View more