Association rule with frequent pattern growth algorithm for frequent item sets mining
Kittipol Wisaeng · Applied Mathematical Sciences · 2014
Frequent item sets mining from the transaction dataset is one of the most challenging problems in data mining approaches. In many real world scenarios, the information is not extracted from a single data source, but from distributed and heterogeneous ones. Therefore, the discovered knowledge in this paper is generating association rules using frequent pattern growth algorithms for transactional market basket analysis dataset is presented. The process of rule discovery is illustrated on a dataset containing transactions of customers of the supermarket. The experimental results show that provides excellent market basket analysis performance even on a big data sets.