Data Mining with Graphical Models

Abstract

The explosion of data stored in commercial or administrational databases calls for intelligent techniques to discover the patterns hidden in them and thus to exploit all available information. Therefore a new line of research has recently been established, which became known under the names "Data Mining" and "Knowledge Discovery in Databases". In this paper we study a popular technique from its arsenal of methods to do dependency analysis, namely learning inference networks (also called "graphical models") from data. We review the already well-known probabilistic networks and provide an introduction to the recently developed and closely related possibilistic networks.