Change-point detection using spectral PCA for multivariate time series

TL;DR

This paper introduces Spec PC-CP, a two-stage spectral PCA-based method for detecting change points in high-dimensional multivariate time series, effectively capturing lead-lag relationships and outperforming existing methods.

Contribution

The paper presents a novel spectral PCA-based approach for change-point detection that captures lead-lag relationships in multivariate time series.

Findings

Outperforms existing methods in simulations

Effectively detects change points in EEG and stock data

Captures lead-lag relationships in time series

Abstract

We propose a two-stage approach Spec PC-CP to identify change points in multivariate time series. In the first stage, we obtain a low-dimensional summary of the high-dimensional time series by Spectral Principal Component Analysis (Spec-PCA). In the second stage, we apply cumulative sum-type test on the Spectral PCA component using a binary segmentation algorithm. Compared with existing approaches, the proposed method is able to capture the lead-lag relationship in time series. Our simulations demonstrate that the Spec PC-CP method performs significantly better than competing methods for detecting change points in high-dimensional time series. The results on epileptic seizure EEG data and stock data also indicate that our new method can efficiently {detect} change points corresponding to the onset of the underlying events.