Detecting Infrequent Weighted Patterns as Outliers using WFPG

摘要

Mining of frequent patterns have attracted great attention in the last few decades due to their vast variety of applications in real life. Recently the problem of detecting outliers from transactional datasets has been considered as the process of mining infrequent patterns. As we know that frequent patterns are those patterns in transactional datasets which are preferred by most of the customers; whereas infrequent patterns are not. Here the concept of outliers is being considered as those patterns which are infrequent at all but their weight count is higher from threshold values. This paper has presented an approach WFPG to detect infrequent weighted patterns from transactional datasets. Experimental work and theoretical analysis show that the WFPG has detected weighted infrequent patterns/ item sets with lower support count as compared to their weight value.