Research in association rule mining is dominated by using Positive Association Rule (PAR) obtained from frequently recurring item sets. While traditional association rule mining primarily concentrates on discovering positive associations between items, recent research has extended its focus to uncover meaningful insights from both frequent and infrequent item sets, which includes the discovery of Negative Association Rule (NARs). The identification of unusual item sets is significantly more challenging than the discovery of common item sets. These issues include the finding of rare item sets, the production of correct NARs and the vast number of NARs as compared to positive association rules. Frequent item sets are generally easy to find, but the subtler and more infrequent item sets are the ones that go unnoticed. Researchers develop a method for identifying patterns of positive and negative correlation between the variables using frequent and rare data sets. A broad range of methods and strategies have been developed by researchers to identify positive and negative associations in data sets. The Frequent Pattern Growth (FP-Growth) technique is a well-established and competent way for locating often occurring item sets without the development of applicant item sets from the current methodologies. In this research, the Apriori algorithm, FP-Growth algorithm and Éclat algorithm are used to find out the occurrence of frequent and infrequent item sets. In recent research, Negative Association Rules have gained attention because they provide a complementary perspective to positive association rules and can uncover hidden relationships and patterns in data. As a result, many item sets with varying minimum support values are generated and the NARs generated with the help of frequent and infrequent item sets are the most effective when compared to others.