Dual-Forecaster: A Multimodal Time Series Model Integrating Descriptive and Predictive Texts
This work addresses the challenge of improving time series forecasting accuracy for applications where textual data is available, representing an incremental advance by combining existing textual modalities more effectively.
The paper tackled the problem of insufficient information in single-modal time series models by proposing Dual-Forecaster, a multimodal model that integrates both historical and predictive textual information with numerical data, achieving performance that outperforms or is comparable to state-of-the-art models on fifteen datasets.
Most existing single-modal time series models rely solely on numerical series, which suffer from the limitations imposed by insufficient information. Recent studies have revealed that multimodal models can address the core issue by integrating textual information. However, these models focus on either historical or future textual information, overlooking the unique contributions each plays in time series forecasting. Besides, these models fail to grasp the intricate relationships between textual and time series data, constrained by their moderate capacity for multimodal comprehension. To tackle these challenges, we propose Dual-Forecaster, a pioneering multimodal time series model that combines both descriptively historical textual information and predictive textual insights, leveraging advanced multimodal comprehension capability empowered by three well-designed cross-modality alignment techniques. Our comprehensive evaluations on fifteen multimodal time series datasets demonstrate that Dual-Forecaster is a distinctly effective multimodal time series model that outperforms or is comparable to other state-of-the-art models, highlighting the superiority of integrating textual information for time series forecasting. This work opens new avenues in the integration of textual information with numerical time series data for multimodal time series analysis.