ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data

TL;DR

ChatTime is a novel multimodal foundation model that unifies numerical and textual time series analysis, enabling zero-shot forecasting and bimodal processing, surpassing traditional unimodal methods.

Contribution

It introduces a framework modeling time series as a language, supporting multimodal input/output and zero-shot forecasting, which is a significant advancement over existing unimodal approaches.

Findings

ChatTime achieves superior performance across multiple tasks.

It demonstrates effective zero-shot forecasting capabilities.

The model supports bimodal input/output for time series and text.

Abstract

Human experts typically integrate numerical and textual multimodal information to analyze time series. However, most traditional deep learning predictors rely solely on unimodal numerical data, using a fixed-length window for training and prediction on a single dataset, and cannot adapt to different scenarios. The powered pre-trained large language model has introduced new opportunities for time series analysis. Yet, existing methods are either inefficient in training, incapable of handling textual information, or lack zero-shot forecasting capability. In this paper, we innovatively model time series as a foreign language and construct ChatTime, a unified framework for time series and text processing. As an out-of-the-box multimodal time series foundation model, ChatTime provides zero-shot forecasting capability and supports bimodal input/output for both time series and text. We design a series of experiments to verify the superior performance of ChatTime across multiple tasks and scenarios, and create four multimodal datasets to address data gaps. The experimental results demonstrate the potential and utility of ChatTime.