An Interpretable Generative Framework for Anomaly Detection in High-Dimensional Financial Time Series
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918379726569472 |
|---|---|
| author | Martinez, Waldyn G |
| author_facet | Martinez, Waldyn G |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07864 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An Interpretable Generative Framework for Anomaly Detection in High-Dimensional Financial Time Series Martinez, Waldyn G Machine Learning 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. |
| title | An Interpretable Generative Framework for Anomaly Detection in High-Dimensional Financial Time Series |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.07864 |