Algorithm for Map/Reduce-based association rules data mining
Wenqi Wang, Qiang Li · 2013
In order to realize massive information data mining, the traditional Apriori algorithm is updated into a Map/Reduce-based frequent itemsets generating method, so as to distribute the massive data into several servers for parallel processing.The construction of Hadoop platform helps to realize this method which is also compared with Apriori algorithm.The experimental results show that, in the process to generate frequent itemsets of massive data, this method can make full use of the advantages of parallel processing, followed by better timeliness.