Date Added: Jan 2013
Over the past generation, the process of discovering interesting association rules in data mining and knowledge discovery has become a cornerstone of contemporary decision support environments. While most of the existing algorithms do indeed focus on discovering high interestingness and accuracy relationships between items in the databases, they tend to have limited scalability and performance. In this paper, the authors discuss a Parallel Genetic Algorithm Model (PGAM) that has been designed as a scalable and high performance association rules engine. Experimental results demonstrate that the model offers the potential to optimize both scalability and performance in association rules mining.