Method for Mining High-utility Patterns in Transaction Stream Data based on Linked List Structure

Mining valuable patterns in data streams presentsa significant challenge in the field of data mining. Thistask is crucial as it allows for the identification of highlyprofitable item sets within transaction databases. However, asnew transactions are continually added, new valuable patternsemerge, thus changing the usefulness of previously analyzeddata. It is essential to promptly update information regardingthese changes to enable effective business decision-making.Consequently, existing mining methods applied to transactionflow datasets require considerable time to identify newpatterns and update information related to new transactions.This article focuses on the research and proposal of a newtransaction stream data mining method called High-UtilityStream Linked-List Mining. The method utilizes a linkedlist structure known as the High-Utility Stream Linked List(HUSLL) to store information about patterns in the database.Mining and updating transaction information are directlyperformed on the HUSLL structure. Experimental resultsdemonstrate that this novel mining method exhibits moreefficient execution times compared to previous solutions.