Mining Positive and Negative Association Rules from Frequent and Infrequent Pattern Using Improved Genetic Algorithm

Abstract

Association Rule Mining becomes a vast area of research in last few decades. The basic idea behind ARM is to mine positive (interesting) and negative (uninteresting) rules from a transaction database. In this paper we have proposed a new model for mining positive and negative association rules. Our proposed model is an integration between two algorithms, the interesting multiple level minimum support (IMLMS) algorithm and genetic algorithm (GA), which propose a new approach for mining positive and negative rules from frequent and infrequent itemset mined in IMLMS model. Our model gives much better results than previous model.