WATCH: Wasserstein Change Point Detection for High-Dimensional Time Series Data

TL;DR

WATCH introduces a Wasserstein distance-based method for detecting change points in high-dimensional time series data, effectively handling multivariate streams and outperforming existing approaches in accuracy and robustness.

Contribution

The paper presents WATCH, a novel change point detection method leveraging Wasserstein distance, specifically designed for high-dimensional and multivariate data streams.

Findings

WATCH accurately detects change points in high-dimensional data.

It outperforms state-of-the-art methods in benchmark tests.

The approach is robust across various real-world datasets.

Abstract

Detecting relevant changes in dynamic time series data in a timely manner is crucially important for many data analysis tasks in real-world settings. Change point detection methods have the ability to discover changes in an unsupervised fashion, which represents a desirable property in the analysis of unbounded and unlabeled data streams. However, one limitation of most of the existing approaches is represented by their limited ability to handle multivariate and high-dimensional data, which is frequently observed in modern applications such as traffic flow prediction, human activity recognition, and smart grids monitoring. In this paper, we attempt to fill this gap by proposing WATCH, a novel Wasserstein distance-based change point detection approach that models an initial distribution and monitors its behavior while processing new data points, providing accurate and robust detection of change points in dynamic high-dimensional data. An extensive experimental evaluation involving a large number of benchmark datasets shows that WATCH is capable of accurately identifying change points and outperforming state-of-the-art methods.