Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern

Xiong, Jiahong; Wang, Chengsen; Sun, Haifeng; Jing, Yuhan; Qi, Qi; Zhuang, Zirui; Zhang, Lei; Liao, Jianxin; Wang, Jingyu

doi:10.24963/ijcai.2025/745

Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern

Jiahong Xiong, Chengsen Wang, Haifeng Sun, Yuhan Jing, Qi Qi, Zirui Zhuang, Lei Zhang, Jianxin Liao, Jingyu Wang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 6696-6704.

https://doi.org/10.24963/ijcai.2025/745

Keywords

Machine Learning: ML: Time series and data streams
Machine Learning: ML: Attention models

Abstract

Accurate forecasting of time series is crucial for many applications in the real world. Conventional methods primarily rely on statistical analysis of historical data, often leading to overfitting and failing to account for background information and constraints imposed by external events. Therefore, introducing large language models (LLMs) with robust textual capabilities holds significant potential. However, due to the inherent limitations of LLMs in handling numerical data, they do not exhibit advantages in precise numerical prediction tasks. Therefore, we propose a framework to integrate LLMs with conventional methods synergistically. Rather than directly outputting numerical predictions, we leverage the capabilities of the LLMs to generate textual temporal patterns, thereby fully utilizing their inherent knowledge and reasoning abilities. Additionally, we introduce a memory network designed to decode these textual representations into a format that numerical models can effectively interpret. This approach not only capitalizes on the strengths of the LLM in text processing but also bridges the gap between textual and numerical data, enhancing the overall predictive performance of the model. Our experimental results demonstrate the framework's effectiveness, achieving state-of-the-art performance on various benchmark datasets.

Jiahong Xiong, Chengsen Wang, Haifeng Sun, Yuhan Jing, Qi Qi, Zirui Zhuang, Lei Zhang, Jianxin Liao, and Jingyu Wang. 2025. Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 6696–6704. https://doi.org/10.24963/ijcai.2025/745

@inproceedings{ijcai2025p745,
  title     = {Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern},
  author    = {Xiong, Jiahong and Wang, Chengsen and Sun, Haifeng and Jing, Yuhan and Qi, Qi and Zhuang, Zirui and Zhang, Lei and Liao, Jianxin and Wang, Jingyu},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {6696--6704},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/745},
  url       = {https://doi.org/10.24963/ijcai.2025/745},
}

TY  - CPAPER
TI  - Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern
AU  - Xiong, Jiahong
AU  - Wang, Chengsen
AU  - Sun, Haifeng
AU  - Jing, Yuhan
AU  - Qi, Qi
AU  - Zhuang, Zirui
AU  - Zhang, Lei
AU  - Liao, Jianxin
AU  - Wang, Jingyu
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 6696
EP  - 6704
DO  - 10.24963/ijcai.2025/745
UR  - https://doi.org/10.24963/ijcai.2025/745
ER  -