Le rôle de l'utilisateur dans un processus d'extraction de règles d'association
Résumé
We propose QUANTMINER, a genetic-based system for mining quantitative association rules. Our algorithm starts with a set of rule templates chosen by the user and then looks dynamically for the "best" intervals for the numeric attributes present in these templates. An optimization criterion based on both support and confidence is used to keep only high quality and interesting rules. In QUANTMINER, the user is highly solicited in order to guide themining process thus avoiding the discovery of hundreds of rules, as it is usually the case in association rule mining.