The GUHA Method in Data Mining

Abstract

Knowledge discovery in databases (KDD) is the process of identifying valid, novel, potentially useful, and ultimately understandable patterns in (often huge) datasets. Data mining is the central step of KDD: the application of computational techniques to find patterns. GUHA is one of the original data mining methods and is based on a special extension of classical logic. In this course we study the mathematical foundations of the GUHA method and LISp-Miner, a computer implementation of GUHA, and look at several real world applications.

1. Does my data contain something interesting? 2. GUHA produces hypotheses 3. GUHA is a logic-theory based approach to data mining 4. More about the foundations of GUHA 5. Introduction to LISp-Miner software 6. The 4ftTask module 7. 4ftTask module continued 8. Statistical quantifiers in 4ftTask 9. Differences between sets 10. Action Miner