Two revised algorithms based on apriori for mining association rules
Weimin Ma, Z. Liu · 2008
Association rule mining is concerned with the discovery of interesting association relationships hidden in databases. Traditional algorithms are only considering the constraints of minimum support and minimum confidence. However, sometimes it is essential to find stronger association rules for decision makers possessing inadequate resources, and sometimes less strong rules are needed. In this paper, we propose two revised algorithms based on Apriori considering the constraints of three factors: minimum support, minimum confidence and minimum interest. In order to reduce the times of scanning a database, we adopt a matrix structure in our algorithms.