2025/12/01 by Simon Leszek, Leszek, Simon
Computer Science · Engineering · #Time Series Analysis and Forecasting #Fault Detection and Control Systems #Data Stream Mining Techniques
paper · pdf · doi:10.48550/arxiv.2512.01562
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.