From "Birds of a Feather" to Data Insights: The Principles, Methods and Applications of Hierarchical Clustering Algorithms

Cluster analysis aims to group similar objects into the same cluster. Hierarchical clustering, as an important method, does not produce a single grouping result but instead constructs a clustering tree that simultaneously presents the grouping structure of the data at different levels of granularity. This paper focuses on hierarchical clustering algorithms. Using a literature review approach, it outlines the basic principles of hierarchical clustering, its two construction approaches, the algorithmic workflow exemplified by AGNES, and linking methods such as single linkage, complete linkage, average linkage, and Ward's method. It also reviews their applications in fields such as bioinformatics, image segmentation, text clustering, and business analytics. The results indicate that hierarchical clustering does not require a predefined number of clusters and offers high interpretability, however, it is computationally complex, its merging decisions are irreversible, and it is sensitive to noise. Integrating hierarchical clustering with partitioning methods such as K-means, or with improved hierarchical algorithms such as BIRCH and CURE, represents an important direction.