A Method for Reasoning with Structured and Continuous Attributes in the INLEN-2 Multistrategy Knowledge Discovery System

Structured attributes have domains (value sets) that are partially ordered sets, typically hierarchies. Such attributes allow knowledge discovery programs to incorporate background knowledge about hierarchical relationships among attribute values. Inductive generalization rules for structured attributes have been developed that take into consideration the type of nodes in the domain hierarchy (anchor or non-anchor) and the type of decision rules to be generated (characteristic, discriminant or minimum complexity). These generalization rules enhance the ability of knowledge discovery system INLEN-2 to exploit the semantic content of the domain knowledge in the process of generating hypotheses. If the dependent attribute (e.g., a decision attribute) is structured, the system generates a system of hierarchically organized rules representing relationships between the values of this attribute and independent attributes. Such a situation often occurs in practice when the decision to be assigned to a situation can be at different levels of abstraction (e.g., this is a liver disease, or this is a liver cancer). Continuous attributes (e.g., physical measurements) are quantized into a hierarchy of values (ranges of values arranged into different levels). These methods are illustrated by an example concerning the discovery of patterns in world economics and demographics.