Publication Type

Journal Article

Version

publishedVersion

Publication Date

3-2023

Abstract

Stock price movements in financial markets are influenced by large volumes of news from diverse sources on the web, e.g., online news outlets, blogs, social media. Extracting useful information from online news for financial tasks, e.g., forecasting stock returns or risks, is, however, challenging due to the low signal-to-noise ratios of such online information. Assessing the relevance of each news article to the price movements of individual stocks is also difficult, even for human experts. In this article, we propose the Guided Global-Local Attention-based Multimodal Heterogeneous Network (GLAM) model, which comprises novel attention-based mechanisms for multimodal sequential and graph encoding, a guided learning strategy, and a multitask training objective. GLAM uses multimodal information, heterogeneous relationships between companies and leverages significant local responses of individual stock prices to online news to extract useful information from diverse global online news relevant to individual stocks for multiple forecasting tasks. Our extensive experiments with multiple datasets show that GLAM outperforms other state-of-the-art models on multiple forecasting tasks and investment and risk management application case-studies.

Keywords

Graph neural networks, transformers, attention mechanisms, time-series forecasting, networks, multimodality, embeddings, finance, natural language processing

Discipline

Communication Technology and New Media | Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

ACM Transactions on the Web

Volume

17

Issue

2

First Page

1

Last Page

24

ISSN

1559-1131

Identifier

10.1145/3532858

Publisher

Association for Computing Machinery (ACM)

Copyright Owner and License

Authors

Additional URL

https://doi.org//10.1145/3532858

Share

COinS