An Interpretable Generative Framework for Anomaly Detection in High-Dimensional Financial Time Series
This work provides a method for financial analysts and institutions to detect anomalies and structural instabilities in high-dimensional financial time series, which is crucial for risk management and decision-making.
This paper addresses the challenge of detecting structural instability and anomalies in high-dimensional financial time series. The proposed ReGEN-TAD framework integrates machine learning with econometric diagnostics, combining joint forecasting and reconstruction to generate a unified anomaly score without labeled data. Experiments show improved robustness to structured deviations and provide economically coherent factor-level attribution.
Detecting structural instability and anomalies in high-dimensional financial time series is challenging due to complex temporal dependence and evolving cross-sectional structure. We propose ReGEN-TAD, an interpretable generative framework that integrates modern machine learning with econometric diagnostics for anomaly detection. The model combines joint forecasting and reconstruction within a refined convolutional--transformer architecture and aggregates complementary signals capturing predictive inconsistency, reconstruction degradation, latent distortion, and volatility shifts. Robust calibration yields a unified anomaly score without labeled data. Experiments on synthetic and financial panels demonstrate improved robustness to structured deviations while enabling economically coherent factor-level attribution.