用新闻事件增强大模型时间序列预测，提升准确率
From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection
- 用大模型代理迭代筛选新闻，模拟人类推理判断
- 融合精选新闻与时间序列，使预测准确率显著提升
- 适合关注事件驱动预测的金融、气象等领域研究者
本文提出一种新方法，利用大语言模型（LLM）和生成代理，通过跨文本与时间序列数据的推理，增强时间序列预测。以语言为媒介，该方法自适应地将社会事件融入预测模型，使新闻内容与时间序列波动对齐，提供更丰富洞察。具体而言，采用基于LLM的代理，迭代过滤无关新闻，并运用类人推理评估预测结果。这使得模型能够分析突发事件与社会行为变化等复杂事件，并持续优化新闻选择逻辑与代理输出的鲁棒性。通过将筛选后的新闻事件与时间序列数据结合，微调预训练的LLM以预测时间序列中的数字序列。实验结果表明，该方法在预测准确性上取得显著提升，暗示了通过有效利用非结构化新闻数据，可能推动时间序列预测范式的变革。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。