FRI-miner: fuzzy rare itemset mining

Data mining is a widely used technology for various real-life applications of data analytics and important to discover valuable association rules in transaction databases. Interesting itemset plays an role many applications, such as market, e-commerce, finance, medical treatment. To date, algorithms based on frequent patterns have been studied, but there are few that focus infrequent or rare patterns. In some cases, itemsets also play applications. this paper, we introduce novel fuzzy-based algorithm called FRI-Miner, which discovers interesting fuzzy quantitative database by applying theory with linguistic meaning. Additionally, FRI-Miner utilizes the fuzzy-list structure store information applies several pruning strategies reduce search space. The experimental results show proposed can fewer more considering value reality. Moreover, it significantly outperforms state-of-the-art terms effectiveness (w.r.t. different types derived patterns) efficiency running time memory usage).