HEPM : High-efficiency pattern mining

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number111068
Journal / PublicationKnowledge-Based Systems
Volume281
Online published14 Oct 2023
Publication statusPublished - 3 Dec 2023

Abstract

Pattern mining (PM) is an important field of data mining and has gained considerable momentum recently, mainly owing to the massive growth of big data. PM often sets attentive objectives such as mining frequent or high utility patterns to obtain attractive patterns. High utility patterns address the defect of frequent patterns that cannot reveal the maximum profit. However, it neglects another vital factor, cost or investment. This paper proposes a new high-efficiency PM problem that considers both utility and investment. The problem aims to find patterns with the maximum profit-to-investment ratio. Our paper is devoted to studying high-efficiency itemsets in transaction databases. We first formulate the criteria for a high-efficiency PM problem. Subsequently, we propose a two-phase algorithm called HEPM and an improved one-phase algorithm called HEPMiner to discover high-efficiency patterns in a transaction database. We design a corresponding pruning strategy within HEPM to reduce the search space. In HEPMiner, we utilize a novel efficiency-list and an estimated efficiency co-occurrence structure in the pruning strategies to further improve the mining performance. Moreover, we derive the upper bounds of efficiency for both algorithms. The experimental results demonstrate the effectiveness and efficiency of our two algorithms. © 2023 Elsevier B.V.

Research Area(s)

  • Data mining, High-efficiency pattern, Pruning strategy, Upper bound

Citation Format(s)

HEPM: High-efficiency pattern mining. / Zhang, Xiaojie; Chen, Guoting; Song, Linqi et al.
In: Knowledge-Based Systems, Vol. 281, 111068, 03.12.2023.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review