CSTS: A Benchmark for the Discovery of Correlation Structures in Time Series Clustering

TL;DR

CSTS is a synthetic benchmark designed to evaluate the ability of clustering algorithms to accurately discover correlation structures in multivariate time series data, addressing a key challenge in validating clustering methods.

Contribution

The paper introduces CSTS, a comprehensive and extensible benchmark for assessing correlation structure discovery in time series clustering, with validated evaluation protocols and a case study.

Findings

Moderate distortion from downsampling affects correlation preservation.

Distribution shifts and sparsification have minimal impact on correlation structures.

CSTS enables precise diagnosis of clustering algorithm limitations.

Abstract

Time series clustering promises to uncover hidden structural patterns in data with applications across healthcare, finance, industrial systems, and other critical domains. However, without validated ground truth information, researchers cannot objectively assess clustering quality or determine whether poor results stem from absent structures in the data, algorithmic limitations, or inappropriate validation methods, raising the question whether clustering is "more art than science" (Guyon et al., 2009). To address these challenges, we introduce CSTS (Correlation Structures in Time Series), a synthetic benchmark for evaluating the discovery of correlation structures in multivariate time series data. CSTS provides a clean benchmark that enables researchers to isolate and identify specific causes of clustering failures by differentiating between correlation structure deterioration and limitations of clustering algorithms and validation methods. Our contributions are: (1) a comprehensive benchmark for correlation structure discovery with distinct correlation structures, systematically varied data conditions, established performance thresholds, and recommended evaluation protocols; (2) empirical validation of correlation structure preservation showing moderate distortion from downsampling and minimal effects from distribution shifts and sparsification; and (3) an extensible data generation framework enabling structure-first clustering evaluation. A case study demonstrates CSTS's practical utility by identifying an algorithm's previously undocumented sensitivity to non-normal distributions, illustrating how the benchmark enables precise diagnosis of methodological limitations. CSTS advances rigorous evaluation standards for correlation-based time series clustering.