TimeCatcher: A Variational Framework for Volatility-Aware Forecasting of Non-Stationary Time Series
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917227323719680 |
|---|---|
| author | Chen, Zhiyu Liu, Minhao Zhang, Yanru |
| author_facet | Chen, Zhiyu Liu, Minhao Zhang, Yanru |
| contents | Recent lightweight MLP-based models have achieved strong performance in time series forecasting by capturing stable trends and seasonal patterns. However, their effectiveness hinges on an implicit assumption of local stationarity assumption, making them prone to errors in long-term forecasting of highly non-stationary series, especially when abrupt fluctuations occur, a common challenge in domains like web traffic monitoring. To overcome this limitation, we propose TimeCatcher, a novel Volatility-Aware Variational Forecasting framework. TimeCatcher extends linear architectures with a variational encoder to capture latent dynamic patterns hidden in historical data and a volatility-aware enhancement mechanism to detect and amplify significant local variations. Experiments on nine real-world datasets from traffic, financial, energy, and weather domains show that TimeCatcher consistently outperforms state-of-the-art baselines, with particularly large improvements in long-term forecasting scenarios characterized by high volatility and sudden fluctuations. Our code is available at https://github.com/ColaPrinceCHEN/TimeCatcher. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20448 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TimeCatcher: A Variational Framework for Volatility-Aware Forecasting of Non-Stationary Time Series Chen, Zhiyu Liu, Minhao Zhang, Yanru Machine Learning I.2.6 Recent lightweight MLP-based models have achieved strong performance in time series forecasting by capturing stable trends and seasonal patterns. However, their effectiveness hinges on an implicit assumption of local stationarity assumption, making them prone to errors in long-term forecasting of highly non-stationary series, especially when abrupt fluctuations occur, a common challenge in domains like web traffic monitoring. To overcome this limitation, we propose TimeCatcher, a novel Volatility-Aware Variational Forecasting framework. TimeCatcher extends linear architectures with a variational encoder to capture latent dynamic patterns hidden in historical data and a volatility-aware enhancement mechanism to detect and amplify significant local variations. Experiments on nine real-world datasets from traffic, financial, energy, and weather domains show that TimeCatcher consistently outperforms state-of-the-art baselines, with particularly large improvements in long-term forecasting scenarios characterized by high volatility and sudden fluctuations. Our code is available at https://github.com/ColaPrinceCHEN/TimeCatcher. |
| title | TimeCatcher: A Variational Framework for Volatility-Aware Forecasting of Non-Stationary Time Series |
| topic | Machine Learning I.2.6 |
| url | https://arxiv.org/abs/2601.20448 |