The Efficient and Complete Frequent Itemsets Mining of Association Rules

Abstract

How to generate the candidate itemsets, how to compute the supporting number of itemsets, how to reduce the size of candidate itemsets and how to decrease the scanning times of transaction databases, are four capital technique difficulties of association rules mining. In this paper, we have presented an new idea that transforms the data structure of transaction databases to the directed graph, and applies the directed itemsets graph to store the relevant information of frequent itemsets of transaction databases, and puts forward trifurcate linked list storage structure of directed itemsets graph, and provides mining algorithm of complete frequent itemsets based on the directed itemsets graph. So the four capital technique difficulties mentioned above are resolved efficiently.

A Survey on Particle Swarm Optimization for Association Rule Mining

“…Most researchers use support and confidence to evaluate rules. The inherent drawback of this is that rare data items with less than the minimum support cannot be studied, and the support-confidence-based evaluation system generates a huge number of invalid rules; thus, other evaluation metrics need to be introduced to further mine the rules of interest to users [29].…”