From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection

Xinlei Wang, Maike Feng, Jing Qiu, Jinjin Gu, Junhua Zhao

Keywords: Large Language Model, Time Series Forecasting, AI Agent

Abstract: This paper introduces a novel approach that leverages Large Language Models (LLMs) and Generative Agents to enhance time series forecasting by reasoning across both text and time series data. With language as a medium, our method adaptively integrates social events into forecasting models, aligning news content with time series fluctuations to provide richer insights. Specifically, we utilize LLM-based agents to iteratively filter out irrelevant news and employ human-like reasoning to evaluate predictions. This enables the model to analyze complex events, such as unexpected incidents and shifts in social behavior, and continuously refine the selection logic of news and the robustness of the agent's output. By integrating selected news events with time series data, we fine-tune a pre-trained LLM to predict sequences of digits in time series. The results demonstrate significant improvements in forecasting accuracy, suggesting a potential paradigm shift in time series forecasting through the effective utilization of unstructured news data.

Primary Area: Machine learning for other sciences and fields

Submission Number: 5288