Learning classification rules based on concept semilattice

Concept lattice is an efficient formal tool for data analysis and knowledge extraction. In this paper, we present an incremental construction algorithm of join-semilattice with a simple example and a novel induction algorithm, rulextracter, which induces classification rules using a semilattice as an explicit map through the search space of rules. Furthermore, our learning system is shown to be robust in the presence of noisy data. The rulextracter system is also capable of learning both decision lists as well as unordered rule sets and thus allows for comparisons of these different learning paradigms within the same algorithmic framework.