Improvement of Apriori Algorithm
Zhao Qing Song, Liquan Sun · Harbin Ligong Daxue xuebao · 2007
Apriori algorithm is the most classical algorithm of all the association rules mining methods,but Apriori algorithm has two faults.Firstly,this algorithm has to scan transaction database many times.Secondly,this algorithm has to produce many candidate itemsets.IThis paper puts forward a new algorithm,this algorithm scans transaction database only one time through adding Tid_list to candidate itemsets C_1,and can reduce the number of candidate itemsets on basis of the character of frequent itemsets,so as to improve the efficiency of Apriori algo- rithm.