MM-iTransformer: A Multimodal Approach to Economic Time Series Forecasting with Textual Data

Mou, Shangyang; Xue, Qiang; Chen, Jinhui; Takiguchi, Tetsuya; Ariki, Yasuo

doi:10.3390/app15031241

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

MM-iTransformer: A Multimodal Approach to Economic Time Series Forecasting with Textual Data

by

Shangyang Mou

^1,*,

Qiang Xue

¹

,

Jinhui Chen

²,

Tetsuya Takiguchi

¹ and

Yasuo Ariki

¹

Graduate School of System Informatics, Kobe University, Kobe 657-8501, Japan

²

Faculty of Systems Engineering, Wakayama University, Wakayama 640-8510, Japan

^*

Author to whom correspondence should be addressed.

Appl. Sci. 2025, 15(3), 1241; https://doi.org/10.3390/app15031241

Submission received: 17 December 2024 / Revised: 19 January 2025 / Accepted: 24 January 2025 / Published: 25 January 2025

Download Versions Notes

Abstract

This paper introduces a novel multimodal framework for economic time series forecasting, integrating textual information with historical price data to enhance predictive accuracy. The proposed method employs a multi-head attention mechanism to dynamically align textual embeddings with temporal price data, capturing previously unrecognized cross-modal dependencies and enhancing the model’s ability to interpret event-driven market dynamics. This enables the framework to model complex market behaviors in a unified and effective manner. Experimental results across multiple financial datasets, including the foreign exchange (Forex) and Gold-price datasets, demonstrate that incorporating textual information significantly enhances forecasting accuracy. Compared to models relying solely on historical price data, the proposed framework achieves a substantial reduction in Mean Squared Error (MSE) loss, with improvements of up to 26.79%. This highlights the effectiveness of leveraging textual inputs alongside structured time series data in capturing complex market dynamics and improving predictive performance.

Keywords: economic time series forecasting; feature engineering; multimodal data fusion; deep learning; data mining

Share and Cite

MDPI and ACS Style

Mou, S.; Xue, Q.; Chen, J.; Takiguchi, T.; Ariki, Y. MM-iTransformer: A Multimodal Approach to Economic Time Series Forecasting with Textual Data. Appl. Sci. 2025, 15, 1241. https://doi.org/10.3390/app15031241

AMA Style

Mou S, Xue Q, Chen J, Takiguchi T, Ariki Y. MM-iTransformer: A Multimodal Approach to Economic Time Series Forecasting with Textual Data. Applied Sciences. 2025; 15(3):1241. https://doi.org/10.3390/app15031241

Chicago/Turabian Style

Mou, Shangyang, Qiang Xue, Jinhui Chen, Tetsuya Takiguchi, and Yasuo Ariki. 2025. "MM-iTransformer: A Multimodal Approach to Economic Time Series Forecasting with Textual Data" Applied Sciences 15, no. 3: 1241. https://doi.org/10.3390/app15031241

APA Style

Mou, S., Xue, Q., Chen, J., Takiguchi, T., & Ariki, Y. (2025). MM-iTransformer: A Multimodal Approach to Economic Time Series Forecasting with Textual Data. Applied Sciences, 15(3), 1241. https://doi.org/10.3390/app15031241

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

MM-iTransformer: A Multimodal Approach to Economic Time Series Forecasting with Textual Data

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI