Adaptive Information Routing for Multimodal Time Series Forecasting

TL;DR

This paper introduces the AIR framework, a novel multimodal time series forecasting method that uses text data to dynamically guide and improve prediction accuracy, validated on real-world market data.

Contribution

The paper presents a new adaptive routing approach that leverages text data to control multivariate time series integration, along with a text-refinement pipeline and a benchmarking platform.

Findings

AIR improves forecasting accuracy on market data

Text-guided modulation enhances model performance

Benchmark facilitates multimodal forecasting experiments

Abstract

Time series forecasting is a critical task for artificial intelligence with numerous real-world applications. Traditional approaches primarily rely on historical time series data to predict the future values. However, in practical scenarios, this is often insufficient for accurate predictions due to the limited information available. To address this challenge, multimodal time series forecasting methods which incorporate additional data modalities, mainly text data, alongside time series data have been explored. In this work, we introduce the Adaptive Information Routing (AIR) framework, a novel approach for multimodal time series forecasting. Unlike existing methods that treat text data on par with time series data as interchangeable auxiliary features for forecasting, AIR leverages text information to dynamically guide the time series model by controlling how and to what extent multivariate time series information should be combined. We also present a text-refinement pipeline that employs a large language model to convert raw text data into a form suitable for multimodal forecasting, and we introduce a benchmark that facilitates multimodal forecasting experiments based on this pipeline. Experiment results with the real world market data such as crude oil price and exchange rates demonstrate that AIR effectively modulates the behavior of the time series model using textual inputs, significantly enhancing forecasting accuracy in various time series forecasting tasks.