Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities

TL;DR

This paper investigates how large language models perform in time series forecasting without fine-tuning, revealing their strengths with patterned data and limitations with non-periodic datasets, and proposes input strategies to improve accuracy.

Contribution

It provides a comparative analysis of LLMs and traditional models, exploring input strategies and their impact on forecasting performance in zero-shot settings.

Findings

LLMs excel with clear patterns and trends in time series data.

They struggle with datasets lacking periodicity.

Incorporating external knowledge improves LLM forecasting accuracy.

Abstract

Large language models (LLMs) have been applied in many fields and have developed rapidly in recent years. As a classic machine learning task, time series forecasting has recently been boosted by LLMs. Recent works treat large language models as \emph{zero-shot} time series reasoners without further fine-tuning, which achieves remarkable performance. However, there are some unexplored research problems when applying LLMs for time series forecasting under the zero-shot setting. For instance, the LLMs' preferences for the input time series are less understood. In this paper, by comparing LLMs with traditional time series forecasting models, we observe many interesting properties of LLMs in the context of time series forecasting. First, our study shows that LLMs perform well in predicting time series with clear patterns and trends, but face challenges with datasets lacking periodicity. This observation can be explained by the ability of LLMs to recognize the underlying period within datasets, which is supported by our experiments. In addition, the input strategy is investigated, and it is found that incorporating external knowledge and adopting natural language paraphrases substantially improve the predictive performance of LLMs for time series. Overall, our study contributes insight into LLMs' advantages and limitations in time series forecasting under different conditions.