Score: 0

Efficient Model Selection for Time Series Forecasting via LLMs

Published: April 2, 2025 | arXiv ID: 2504.02119v1

By: Wang Wei , Tiankai Yang , Hongjie Chen and more

Potential Business Impact:

AI picks best computer models for predicting future.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

Model selection is a critical step in time series forecasting, traditionally requiring extensive performance evaluations across various datasets. Meta-learning approaches aim to automate this process, but they typically depend on pre-constructed performance matrices, which are costly to build. In this work, we propose to leverage Large Language Models (LLMs) as a lightweight alternative for model selection. Our method eliminates the need for explicit performance matrices by utilizing the inherent knowledge and reasoning capabilities of LLMs. Through extensive experiments with LLaMA, GPT and Gemini, we demonstrate that our approach outperforms traditional meta-learning techniques and heuristic baselines, while significantly reducing computational overhead. These findings underscore the potential of LLMs in efficient model selection for time series forecasting.

Country of Origin
πŸ‡ΊπŸ‡Έ United States

Page Count
16 pages

Category
Computer Science:
Machine Learning (CS)