Multimodal deep learning for finance: integrating and forecasting international stock markets
- PDF / 2,207,664 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 110 Downloads / 163 Views
Multimodal deep learning for finance: integrating and forecasting international stock markets Sang Il Lee1 · Seong Joon Yoo1
© Springer Science+Business Media, LLC, part of Springer Nature 2019
Abstract In today’s increasingly international economy, return and volatility spillover effects across international equity markets are major macroeconomic drivers of stock dynamics. Thus, information regarding foreign markets is one of the most important factors in forecasting domestic stock prices. However, the cross-correlation between domestic and foreign markets is highly complex. Hence, it is extremely difficult to explicitly express this cross-correlation with a dynamical equation. In this study, we develop stock return prediction models that can jointly consider international markets, using multimodal deep learning. Our contributions are threefold: (1) we visualize the transfer information between South Korea and US stock markets by using scatter plots; (2) we incorporate the information into the stock prediction models with the help of multimodal deep learning; (3) we conclusively demonstrate that the early and intermediate fusion models achieve a significant performance boost in comparison with the late fusion and single-modality models. Our study indicates that jointly considering international stock markets can improve the prediction accuracy and deep neural networks are highly effective for such tasks. Keywords Stock prediction · Deep neural networks · Multimodal · Data fusion · International stock markets
1 Introduction 1.1 Aims and scope of the study The interdependence between international stock markets has been steadily increasing in recent years. In particular, after the stock market crash of 1987, the * Seong Joon Yoo [email protected] Sang Il Lee [email protected] 1
Department of Computer Engineering, Sejong University, Seoul, Republic of Korea
13
Vol.:(0123456789)
S. I. Lee, S. J. Yoo
interdependence increased significantly [1], and more recently, this interdependence was widely noticed during the global financial crisis of 2007 [2]. Both originated in the US and resulted in a sharp decline in the stock prices of international stock markets, rapidly spreading to other countries. The crisis clearly confirmed that the financial events originating in one market are not isolated to that particular market but are also transmissible across international borders. Currently, this internationalization is a common phenomenon and expected to accelerate. The goal of our study is to investigate the contribution of additional international market information in stock prediction by using deep learning. Typically, this interconnection has not been considered in stock prediction unlike various data categories such as country-specific price, macroeconomic, news, and fundamental data. We considered the South Korean and US stock markets with non-overlapping stock exchange trading hours as a case study and studied the one-day-ahead stock return prediction of the South Korean stock market by combining the d
Data Loading...
