Empowering Time Series Forecasting with LLM-Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908676289200128 |
|---|---|
| author | Yeh, Chin-Chia Michael Lai, Vivian Saini, Uday Singh Fan, Xiran Fan, Yujie Wang, Junpeng Dai, Xin Zheng, Yan |
| author_facet | Yeh, Chin-Chia Michael Lai, Vivian Saini, Uday Singh Fan, Xiran Fan, Yujie Wang, Junpeng Dai, Xin Zheng, Yan |
| contents | Large Language Model (LLM) powered agents have emerged as effective planners for Automated Machine Learning (AutoML) systems. While most existing AutoML approaches focus on automating feature engineering and model architecture search, recent studies in time series forecasting suggest that lightweight models can often achieve state-of-the-art performance. This observation led us to explore improving data quality, rather than model architecture, as a potentially fruitful direction for AutoML on time series data. We propose DCATS, a Data-Centric Agent for Time Series. DCATS leverages metadata accompanying time series to clean data while optimizing forecasting performance. We evaluated DCATS using four time series forecasting models on a large-scale traffic volume forecasting dataset. Results demonstrate that DCATS achieves an average 6% error reduction across all tested models and time horizons, highlighting the potential of data-centric approaches in AutoML for time series forecasting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04231 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Empowering Time Series Forecasting with LLM-Agents Yeh, Chin-Chia Michael Lai, Vivian Saini, Uday Singh Fan, Xiran Fan, Yujie Wang, Junpeng Dai, Xin Zheng, Yan Machine Learning Artificial Intelligence Large Language Model (LLM) powered agents have emerged as effective planners for Automated Machine Learning (AutoML) systems. While most existing AutoML approaches focus on automating feature engineering and model architecture search, recent studies in time series forecasting suggest that lightweight models can often achieve state-of-the-art performance. This observation led us to explore improving data quality, rather than model architecture, as a potentially fruitful direction for AutoML on time series data. We propose DCATS, a Data-Centric Agent for Time Series. DCATS leverages metadata accompanying time series to clean data while optimizing forecasting performance. We evaluated DCATS using four time series forecasting models on a large-scale traffic volume forecasting dataset. Results demonstrate that DCATS achieves an average 6% error reduction across all tested models and time horizons, highlighting the potential of data-centric approaches in AutoML for time series forecasting. |
| title | Empowering Time Series Forecasting with LLM-Agents |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2508.04231 |