Using Decision Trees for Interpretable Supervised Clustering

TL;DR

This paper introduces an iterative decision tree-based method for interpretable supervised clustering, aiming to find high-density, class-specific clusters with descriptive rules in labeled datasets.

Contribution

It presents a novel approach combining decision trees with supervised clustering to produce explainable, high-density class-specific clusters.

Findings

Effective extraction of interpretable clusters demonstrated

Method improves cluster quality and interpretability

Applicable to various labeled datasets

Abstract

In this paper, we address an issue of finding explainable clusters of class-uniform data in labelled datasets. The issue falls into the domain of interpretable supervised clustering. Unlike traditional clustering, supervised clustering aims at forming clusters of labelled data with high probability densities. We are particularly interested in finding clusters of data of a given class and describing the clusters with the set of comprehensive rules. We propose an iterative method to extract high-density clusters with the help of decisiontree-based classifiers as the most intuitive learning method, and discuss the method of node selection to maximize quality of identified groups.