Depth-based clustering analysis of directional data

TL;DR

This paper introduces a non-parametric, depth-based clustering method for directional data, effective in high dimensions, validated through simulations and a real text mining example.

Contribution

It presents a novel depth-based clustering approach for directional data that is flexible, non-parametric, and suitable for high-dimensional applications.

Findings

Effective in high-dimensional settings

Outperforms existing directional clustering algorithms

Validated through simulations and real data

Abstract

A new depth-based clustering procedure for directional data is proposed. Such method is fully non-parametric and has the advantages to be flexible and applicable even in high dimensions when a suitable notion of depth is adopted. The introduced technique is evaluated through an extensive simulation study. In addition, a real data example in text mining is given to explain its effectiveness in comparison with other existing directional clustering algorithms.