HOS-Miner: A System for Detecting Outlying Subspaces of High-dimensional Data Ji Zhang, Meng Lou, Tok Wang Ling, and Hai Wang   View Paper (PDF)   Return to DEMO GROUP 1: DATA MINING Abstract We identify a new and interesting high-dimensional outlier detection problem in this paper, that is, detecting the subspaces in which given data points are outliers. We call the subspaces in which a data point is an outlier as its Outlying Subspaces. In this paper, we will propose the prototype of a dynamic subspace search system, called HOS-Miner (HOS stands for High-dimensional Outlying Subspaces), that utilizes a sample-based learning process to effectively identify the outlying subspaces of a given point. ©2005 Association for Computing Machinery