A Fast and Effective Tree-based Mining Technique for Extraction of High Utility Itemsets

Abstract

The most important phase in the discovery of common item-sets is identifying relationships between the items. Frequent-pattern growth (FP-growth), one of the traditional association mining techniques, excels at generating frequent item sets. For the purpose of eliminating item sets with high infrequency, both mining algorithms employ the support-confidence framework. Due to its inability to take into account the affected utility element, the support-confidence framework falls short in important applications including e-commerce, web mining, and healthcare. For circumvent the drawbacks of conventional algorithms, utility-based mining methods must be developed. Utility-based mining algorithms have recently developed with the significant advancements in association mining. For the purpose of performing active utility mining, the proposed technique is described. It employed the utility mining algorithms by tree structure building. The experimental section shows experimental findings from benchmark datasets and illustrates the effectiveness of the proposed methodology.