Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecasting

Abstract

Existing time series forecasting methods primarily rely on the numerical data itself. However, real-world time series exhibit complex patterns associated with multimodal information, making them difficult to predict with numerical data alone. While several multimodal time series forecasting methods have emerged, they either utilize text with limited supplementary information or focus merely on representation extraction, extracting minimal textual information for forecasting. To unlock the Value of Text, we propose VoT, a method with Event-driven Reasoning and Multi-level Alignment. Event-driven Reasoning combines the rich information in exogenous text with the powerful reasoning capabilities of LLMs for time series forecasting. To guide the LLMs in effective reasoning, we propose the Historical In-context Learning that retrieves and applies historical examples as in-context guidance. To maximize the utilization of text, we propose Multi-level Alignment. At the representation level, we utilize the Endogenous Text Alignment to integrate the endogenous text information with the time series. At the prediction level, we design the Adaptive Frequency Fusion to fuse the frequency components of event-driven prediction and numerical prediction to achieve complementary advantages. Experiments on real-world datasets across 10 domains demonstrate significant improvements over existing methods, validating the effectiveness of our approach in the utilization of text. The code is made available at https://github.com/decisionintelligence/VoT.

Figures (10)

• Figure 1: Unemployment rate time series time-mmd (1970-2020). While certain patterns (pink) exhibit predictable temporal regularities, abrupt changes (green) driven by external events necessitate the integration of textual information to complement numerical forecasting.
• Figure 2: The architecture of VoT. The event-driven branch processes exogenous text through a three-step generative pipeline with the Historical In-Context Learning (HIC). The numerical branch aligns endogenous text with time series via the Endogenous Text Alignment (ETA). The Adaptive Frequency Fusion (AFF) combines both predictions across frequency bands with adaptive weights.
• Figure 3: The processing procedure of the Historical In-Context Learning.
• Figure 4: The processing procedure of the Endogenous Text Alignment (ETA).
• Figure 4: Ablation study results on Energy and Social Good datasets