Some Mathematical Aspects of Cluster Analysis

Richard McGehee, Department of Mathematics, UMN

Cluster analysis, a data mining technique applied to such diverse areas as marketing, homeland security, and medical research, has a simple mathematical formulation. Although cluster analysis has been in use for at least 35 years, there appear to be some unresolved mathematical questions underlying some of the common computational techniques used for analyzing large data sets. In this lecture, I present an overview of the subject and pose some open questions.