Towards Explainable Deep Clustering for Time Series Data

TL;DR

This survey reviews current methods in explainable deep clustering for time series, highlighting their architectures, limitations, and proposing future research directions to enhance interpretability and real-world applicability.

Contribution

It provides a comprehensive overview of explainable deep clustering techniques for time series and outlines six key research opportunities to advance the field.

Findings

Most methods use autoencoder and attention architectures.

Limited support for streaming and irregularly sampled data.

Interpretability is often an add-on rather than a core feature.

Abstract

Deep clustering uncovers hidden patterns and groups in complex time series data, yet its opaque decision-making limits use in safety-critical settings. This survey offers a structured overview of explainable deep clustering for time series, collecting current methods and their real-world applications. We thoroughly discuss and compare peer-reviewed and preprint papers through application domains across healthcare, finance, IoT, and climate science. Our analysis reveals that most work relies on autoencoder and attention architectures, with limited support for streaming, irregularly sampled, or privacy-preserved series, and interpretability is still primarily treated as an add-on. To push the field forward, we outline six research opportunities: (1) combining complex networks with built-in interpretability; (2) setting up clear, faithfulness-focused evaluation metrics for unsupervised explanations; (3) building explainers that adapt to live data streams; (4) crafting explanations tailored to specific domains; (5) adding human-in-the-loop methods that refine clusters and explanations together; and (6) improving our understanding of how time series clustering models work internally. By making interpretability a primary design goal rather than an afterthought, we propose the groundwork for the next generation of trustworthy deep clustering time series analytics.