Data clustering: a fundamental method in data science and management
Duy-Tai Dinh, Hauchi Wong, Daniil Lisik, Michal Koren, Dat Tran, Philip S. Yu, Joaquín Torres-Sospedra
Abstract
This study investigates the pivotal role of data clustering in both data science and management, focusing on core methodologies, tools, and diverse applications. It examines traditional clustering techniques such as partitional and hierarchical methods, alongside more advanced approaches, including data stream, density-based, graph-based, and model-based clustering, which are essential for processing complex and structured datasets. The study highlights fundamental principles, presents commonly adapted tools and frameworks, outlines the clustering workflow within data science, and discusses major implementation challenges. Beyond technical applications, this study emphasizes how clustering supports managerial tasks and decision-making through a comprehensive survey of recent literature. By bridging analytical techniques with real-world business needs, clustering remains an essential tool in both data science and management. The study concludes by outlining future research directions, underscoring the role of clustering in driving innovation and enabling informed strategic and operational decisions.