Abstract
This article presents the design and implementation of a software tool, PROXIMUS, for error-bounded approximation of high-dimensional binary attributed datasets based on nonorthogonal decomposition of binary matrices. This tool can be used for analyzing data arising in a variety of domains ranging from commercial to scientific applications. Using a combination of innovative algorithms, novel data structures, and efficient implementation, PROXIMUS demonstrates excellent accuracy, performance, and scalability to large datasets. We experimentally demonstrate these on diverse applications in association rule mining and DNA microarray analysis. In limited beta release, PROXIMUS currently has over 300 installations in over 10 countries.
