Many data mining applications involve finding cases that are "similar" to other cases. In Clustering, we want to cluster "similar" customers together. In Link Prediction, we are trying to form linkages between cases based upon how "similar" they are. What do we mean when we say you look like your sister or father? Can you "measure" similarity? This is a broad open-ended question that can lead in many directions. I am looking for your thoughts on defining, measuring and using "similarity" in decision-making.