Mineração de regras de associação temporais quantitativas por meio de algoritmo genético

Association rule mining has shown great potential to extract knowledge from multidimensional data sets. However, existing methods in the literature are not effectively applicable to quantitative temporal data. This article extends the concepts of association rule mining from the literature. Based on the extended concepts is presented a method to mine rules from multidimensional temporal quantitative data sets using genetic algorithm, called GTARGA, in reference to Quantitative Temporal Association Rule Mining by Genetic Algorithm. Experiments with QTARGA in four real data sets show that it allows to mine several high-confidence rules in a single execution of the method.