TimePred: efficient and interpretable offline change point detection for high volume data - with application to industrial process monitoring
This addresses scalability and interpretability issues in industrial process monitoring, representing an incremental improvement with practical domain-specific applications.
The paper tackles the challenge of change-point detection in high-dimensional, large-volume time series by introducing TimePred, a self-supervised framework that reduces multivariate detection to univariate mean-shift detection. The result shows competitive performance while reducing computational cost by up to two orders of magnitude.
Change-point detection (CPD) in high-dimensional, large-volume time series is challenging for statistical consistency, scalability, and interpretability. We introduce TimePred, a self-supervised framework that reduces multivariate CPD to univariate mean-shift detection by predicting each sample's normalized time index. This enables efficient offline CPD using existing algorithms and supports the integration of XAI attribution methods for feature-level explanations. Our experiments show competitive CPD performance while reducing computational cost by up to two orders of magnitude. In an industrial manufacturing case study, we demonstrate improved detection accuracy and illustrate the practical value of interpretable change-point insights.