Research on judgment criterion of association rules
Luo Ke · Kongzhi yu juece · 2003
Mining association rules are an important topic in the data mining research. The reasons for many invalid rules in mining association rules are analyzed. The validity is defined and added to the judgment criterion. According to the value of validity, association rules are classified into positive, invalid and negative association rules. An algorithm of new judgment criterion in mining association rules is presented and tested with Visual FoxPro. The test results show that the method can obviously reduce invalid association rules.