TimePred: efficient and interpretable offline change point detection for high volume data - with application to industrial process monitoring
By: Simon Leszek
Potential Business Impact:
Finds problems in data faster and cheaper.
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.
Similar Papers
On Multi-entity, Multivariate Quickest Change Point Detection
Signal Processing
Finds when groups of things start acting weird.
Conformal Prediction for Time-series Forecasting with Change Points
Machine Learning (CS)
Helps computers guess future numbers even when they change.
From Observations to Parameters: Detecting Changepoint in Nonlinear Dynamics with Simulation-based Inference
Machine Learning (CS)
Finds hidden changes in messy data patterns.