Using association rules to mine for strong approximate dependencies

Autores: Daniel Sánchez, José María Serrano, Ignacio Blanco, María José Martín Bautista , María-Amparo Vila
Localización: Data mining and knowledge discovery, ISSN 1384-5810, Vol. 16, Nº 3, 2008, págs. 313-348
Idioma: inglés
DOI: 10.1007/s10618-008-0092-3
Texto completo no disponible (Saber más ...)
Resumen
- In this paper we deal with the problem of mining for approximate dependencies (AD) in relational databases. We introduce a definition of AD based on the concept of association rule, by means of suitable definitions of the concepts of item and transaction. This definition allow us to measure both the accuracy and support of an AD. We provide an interpretation of the new measures based on the complexity of the theory (set of rules) that describes the dependence, and we employ this interpretation to compare the new measures with existing ones. A methodology to adapt existing association rule mining algorithms to the task of discovering ADs is introduced. The adapted algorithms obtain the set of ADs that hold in a relation with accuracy and support greater than user-defined thresholds. The experiments we have performed show that our approach performs reasonably well over large databases with real-world data.