Empowering Time Series Forecasting with LLM-Agents
This work addresses the challenge of enhancing forecasting accuracy in time series data for domains like traffic management, representing an incremental improvement in AutoML by shifting focus to data-centric methods.
The paper tackled the problem of improving time series forecasting by focusing on data quality rather than model architecture, proposing DCATS, a data-centric agent that uses metadata to clean data, which resulted in an average 6% error reduction across models and time horizons.
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.