Algorithms for High Utility Pattern Mining

Pattern mining is a research field that deals with extracting knowledge from data to better comprehend it and to support information and decision-making. The utility of a pattern can be characterized as an ordering of preferences over a pool of options and, consequently, is a subjective measure; the utility of a pattern can be actually assessed from very different perspectives and at different abstraction levels. The basic assumption in classical High Utility Pattern Mining (HUPM) is that each item in the database is associated with one, static utility. In this paper we first review the main existing approaches for HUPM and then we introduce some recent extensions allowing to cope with this limitation and to address interesting problems also in the bioinformatics arena. © 2024 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.