Association Rule Mining is the significant way to extract knowledge from data sets. The association among the instance of a dataset can measured with Interestingness Measures (IM) metrics. IM define how much interesting the extract knowledge is. Researchers have proved that the classical Support-Confidence metrics can’t extract the real knowledge and they have been proposing different IM. From a user perspective it’s really tough to select the minimal and best measures from them. From our experiment, the correlation among the various IM such as Support, Confidence, Lift, Cosine, Jaccard, Leverage etc. are evaluated in different popular data sets. In this paper our contribution is to find the correlation among the IM with different ranges in different types of data sets which were not applied in past researches. This study also identified that the correlation varies from data set to data set and proposed a solution based on multiple criterion that will help the users to select the minimal and best from a large number of IM.