Cross-domain deep learning approach for multiple financial market prediction

Xinxin Jiang, Shirui Pan, Jing Jiang, Guodong Long

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Over recent decades, globalization has resulted in a steady increase in cross-border financial flows around the world. To build an abstract representation of a real-world financial market situation, we structure the fundamental influences among homogeneous and heterogeneous markets with three types of correlations: The inner-domain correlation between homogeneous markets in various countries, the cross-domain correlation between heterogeneous markets, and the time-series correlation between current and past markets. Such types of correlations in global finance challenge traditional machine learning approaches due to model complexity and nonlinearity. In this paper, we propose a novel cross-domain deep learning approach (Cd-DLA) to learn real-world complex correlations for multiple financial market prediction. Based on recurrent neural networks, which capture the time-series interactions in financial data, our model utilizes the attention mechanism to analyze the inner-domain and cross-domain correlations, and then aggregates all of them for financial forecasting. Experiment results on ten-year financial data on currency and stock markets from three countries prove the performance of our approach over other baselines.

Original languageEnglish
Title of host publication2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings
EditorsLeandro Minku, Rodrigo Soares
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages2191-2198
Number of pages8
ISBN (Electronic)9781509060146
ISBN (Print)9781509060153
DOIs
Publication statusPublished - 2018
Externally publishedYes
EventIEEE International Joint Conference on Neural Networks 2018 - Rio de Janeiro, Brazil
Duration: 8 Jul 201813 Jul 2018
Conference number: 2018
http://www.ecomp.poli.br/~wcci2018/

Conference

ConferenceIEEE International Joint Conference on Neural Networks 2018
Abbreviated titleIJCNN 2018
CountryBrazil
CityRio de Janeiro
Period8/07/1813/07/18
Internet address

Keywords

  • attention neural network
  • deep learning
  • financial analysis

Cite this

Jiang, X., Pan, S., Jiang, J., & Long, G. (2018). Cross-domain deep learning approach for multiple financial market prediction. In L. Minku, & R. Soares (Eds.), 2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings (pp. 2191-2198). [8489360] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IJCNN.2018.8489360
Jiang, Xinxin ; Pan, Shirui ; Jiang, Jing ; Long, Guodong. / Cross-domain deep learning approach for multiple financial market prediction. 2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings. editor / Leandro Minku ; Rodrigo Soares. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 2191-2198
@inproceedings{efdd897ed95141ae848bb523f0ac8aa4,
title = "Cross-domain deep learning approach for multiple financial market prediction",
abstract = "Over recent decades, globalization has resulted in a steady increase in cross-border financial flows around the world. To build an abstract representation of a real-world financial market situation, we structure the fundamental influences among homogeneous and heterogeneous markets with three types of correlations: The inner-domain correlation between homogeneous markets in various countries, the cross-domain correlation between heterogeneous markets, and the time-series correlation between current and past markets. Such types of correlations in global finance challenge traditional machine learning approaches due to model complexity and nonlinearity. In this paper, we propose a novel cross-domain deep learning approach (Cd-DLA) to learn real-world complex correlations for multiple financial market prediction. Based on recurrent neural networks, which capture the time-series interactions in financial data, our model utilizes the attention mechanism to analyze the inner-domain and cross-domain correlations, and then aggregates all of them for financial forecasting. Experiment results on ten-year financial data on currency and stock markets from three countries prove the performance of our approach over other baselines.",
keywords = "attention neural network, deep learning, financial analysis",
author = "Xinxin Jiang and Shirui Pan and Jing Jiang and Guodong Long",
year = "2018",
doi = "10.1109/IJCNN.2018.8489360",
language = "English",
isbn = "9781509060153",
pages = "2191--2198",
editor = "Leandro Minku and Rodrigo Soares",
booktitle = "2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Jiang, X, Pan, S, Jiang, J & Long, G 2018, Cross-domain deep learning approach for multiple financial market prediction. in L Minku & R Soares (eds), 2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings., 8489360, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 2191-2198, IEEE International Joint Conference on Neural Networks 2018, Rio de Janeiro, Brazil, 8/07/18. https://doi.org/10.1109/IJCNN.2018.8489360

Cross-domain deep learning approach for multiple financial market prediction. / Jiang, Xinxin; Pan, Shirui; Jiang, Jing; Long, Guodong.

2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings. ed. / Leandro Minku; Rodrigo Soares. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 2191-2198 8489360.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Cross-domain deep learning approach for multiple financial market prediction

AU - Jiang, Xinxin

AU - Pan, Shirui

AU - Jiang, Jing

AU - Long, Guodong

PY - 2018

Y1 - 2018

N2 - Over recent decades, globalization has resulted in a steady increase in cross-border financial flows around the world. To build an abstract representation of a real-world financial market situation, we structure the fundamental influences among homogeneous and heterogeneous markets with three types of correlations: The inner-domain correlation between homogeneous markets in various countries, the cross-domain correlation between heterogeneous markets, and the time-series correlation between current and past markets. Such types of correlations in global finance challenge traditional machine learning approaches due to model complexity and nonlinearity. In this paper, we propose a novel cross-domain deep learning approach (Cd-DLA) to learn real-world complex correlations for multiple financial market prediction. Based on recurrent neural networks, which capture the time-series interactions in financial data, our model utilizes the attention mechanism to analyze the inner-domain and cross-domain correlations, and then aggregates all of them for financial forecasting. Experiment results on ten-year financial data on currency and stock markets from three countries prove the performance of our approach over other baselines.

AB - Over recent decades, globalization has resulted in a steady increase in cross-border financial flows around the world. To build an abstract representation of a real-world financial market situation, we structure the fundamental influences among homogeneous and heterogeneous markets with three types of correlations: The inner-domain correlation between homogeneous markets in various countries, the cross-domain correlation between heterogeneous markets, and the time-series correlation between current and past markets. Such types of correlations in global finance challenge traditional machine learning approaches due to model complexity and nonlinearity. In this paper, we propose a novel cross-domain deep learning approach (Cd-DLA) to learn real-world complex correlations for multiple financial market prediction. Based on recurrent neural networks, which capture the time-series interactions in financial data, our model utilizes the attention mechanism to analyze the inner-domain and cross-domain correlations, and then aggregates all of them for financial forecasting. Experiment results on ten-year financial data on currency and stock markets from three countries prove the performance of our approach over other baselines.

KW - attention neural network

KW - deep learning

KW - financial analysis

UR - http://www.scopus.com/inward/record.url?scp=85056490365&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2018.8489360

DO - 10.1109/IJCNN.2018.8489360

M3 - Conference Paper

SN - 9781509060153

SP - 2191

EP - 2198

BT - 2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings

A2 - Minku, Leandro

A2 - Soares, Rodrigo

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Jiang X, Pan S, Jiang J, Long G. Cross-domain deep learning approach for multiple financial market prediction. In Minku L, Soares R, editors, 2018 International Joint Conference on Neural Networks (IJCNN) - 2018 Proceedings. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 2191-2198. 8489360 https://doi.org/10.1109/IJCNN.2018.8489360