A NOVEL ALGORITHM FOR FREQUENT ITEM-SETS MINING USING REDUCED DATABASE SCAN APPROACH

Association rule mining is one of the techniques of data mining by which valuable but hidden patterns (knowledge) are discovered from large amount of data. Mining of frequent item sets from which association rules are made, is a most challenging task. No. of algorithms had been developed for frequent item set mining, all differ in various aspects. In this paper a novel algorithm which we are calling as frequent 2-base is presented to mine frequent item sets in two database scans. The time taken by frequent 2-base is also compared with respect to various dimensions. Three dimensions are used to compare the time: database size, no. of items and average transaction size.