Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition
This work addresses the challenge of efficient and accurate time series analysis for users needing flexible LLM applications, though it appears incremental by building on existing prompting techniques.
The paper tackles the problem of time series forecasting with Large Language Models (LLMs) by proposing a simple prompt-based method that avoids heavy fine-tuning and complex architectures, resulting in enhanced forecasting quality with minimal data preprocessing.
Recent advances in Large Language Models (LLMs) have demonstrated new possibilities for accurate and efficient time series analysis, but prior work often required heavy fine-tuning and/or ignored inter-series correlations. In this work, we explore simple and flexible prompt-based strategies that enable LLMs to perform time series forecasting without extensive retraining or the use of a complex external architecture. Through the exploration of specialized prompting methods that leverage time series decomposition, patch-based tokenization, and similarity-based neighbor augmentation, we find that it is possible to enhance LLM forecasting quality while maintaining simplicity and requiring minimal preprocessing of data. To this end, we propose our own method, PatchInstruct, which enables LLMs to make precise and effective predictions.