Interpretable Clustering using Unsupervised Binary Trees

TL;DR

This paper introduces an interpretable clustering method based on unsupervised binary trees, involving recursive splitting, pruning, and joining to produce meaningful clusters with proven consistency, demonstrated on various datasets.

Contribution

The paper presents a novel three-stage interpretable clustering approach using unsupervised binary trees, with theoretical consistency guarantees and practical validation.

Findings

Method achieves interpretable clusters with consistency guarantees.

Effective on simulated and real datasets.

Provides a new framework for unsupervised binary tree clustering.

Abstract

We herein introduce a new method of interpretable clustering that uses unsupervised binary trees. It is a three-stage procedure, the first stage of which entails a series of recursive binary splits to reduce the heterogeneity of the data within the new subsamples. During the second stage (pruning), consideration is given to whether adjacent nodes can be aggregated. Finally, during the third stage (joining), similar clusters are joined together, even if they do not descend from the same node originally. Consistency results are obtained, and the procedure is used on simulated and real data sets.