Abstract
Globalization has posed challenges to financial risk management, connecting markets with each other, and making it more difficult to diversify the portfolio to uncorrelated markets than ever in history. In light of this growing complexity of causal relationships between global stock markets, nonlinear Granger causality has superseded its linear counterpart in providing quantitative evidence for these relationships. In this paper, we propose a hybrid system that extends existing nonlinear Granger causality frameworks using machine learning-based time series prediction models. We improve the accuracy of identifying nonlinear Granger causality by combining p-values of causality statistics from individual machine learning models. By adjusting a model independence coefficient, our model is generalized to datasets where the strength of causality varies. Meanwhile, the causality statistic is still interpretable, because the distribution and critical value are known. Our findings challenge the current understanding that the United States market has the dominating influence and show that Asian markets play a significant role in spreading financial risk worldwide.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Our code as well as supplementary materials are provided at https://github.com/cloudy-sfu/GC-significance-test.
- 2.
Source: https://finance.yahoo.com/world-indices, extracted using the yfinance PyPI package.
References
Al-Yahyaee, K.H., Mensi, W., Al-Jarrah, I.M.W., Tiwari, A.K.: Testing for the Granger-causality between returns in the US and GIPSI stock markets. Physica A 531, 120950 (2019)
Balcilar, M., Elsayed, A., Hammoudeh, S.: Financial connectedness and risk transmission among MENA countries: Evidence from connectedness network and clustering analysis. J. Int. Financial Markets, Inst. Money, p. 101656 (2022)
Baumohl, E., Vyrost, T.: Stock market integration: granger causality testing with respect to nonsynchronous trading effects. Finance a Uver: Czech J. Econ. Finance 61(1) (2011)
Birnbaum, A.: Combining independent tests of significance. J. Am. Stat. Assoc. 49(267), 559–574 (1954)
Brown, M.B.: 400: A method for combining non-independent, one-sided tests of significance. Biometrics, pp. 987–992 (1975)
Chartrand, R.: Numerical differentiation of noisy, nonsmooth data. International Scholarly Research Notices 2011 (2011)
Choi, S.Y.: Credit risk interdependence in global financial markets: evidence from three regions using multiple and partial wavelet approaches. J. Int. Finan. Markets. Inst. Money 80, 101636 (2022)
Gao, W., Yang, H.: Time-varying group lasso Granger causality graph for high dimensional dynamic system. Pattern Recognition, p. 108789 (2022)
Granger, C.W.: Investigating causal relations by econometric models and cross-spectral methods. Econometrica: J. Econometric Soc., 424–438 (1969)
Huang, W., Lai, P.C., Bessler, D.A.: On the changing structure among Chinese equity markets: Hong Kong, Shanghai, and Shenzhen. Eur. J. Oper. Res. 264(3), 1020–1032 (2018)
Karimi, A., Paul, M.R.: Extensive chaos in the Lorenz-96 model. Chaos Interdisciplinary J. Nonlinear Sci. 20(4), 043105 (2010)
Ko, H.H., Ogaki, M.: Granger causality from exchange rates to fundamentals: what does the bootstrap test show us? Int. Rev. Econ. Finance 38, 198–206 (2015)
Kolassa, J.E.: Edgeworth approximations for rank sum test statistics. Stat. Probability Lett. 24(2), 169–171 (1995)
Kost, J.T., McDermott, M.P.: Combining dependent p-values. Stat. Probability Lett. 60(2), 183–190 (2002)
Koumou, G.B.: Diversification and portfolio theory: a review. Fin. Markets. Portfolio Mgmt. 34(3), 267–312 (2020). https://doi.org/10.1007/s11408-020-00352-6
Kwan, C.H.: The China-US trade war: deep-rooted causes, shifting focus and uncertain prospects. Asian Econ. Policy Rev. 15(1), 55–72 (2020)
Leng, S., Xu, Z., Ma, H.: Reconstructing directional causal networks with random forest: Causality meeting machine learning. Chaos: Interdisciplinary J. Nonlinear Sci. 29(9), 093130 (2019)
Marinazzo, D., Pellicoro, M., Stramaglia, S.: Kernel method for nonlinear Granger causality. Phys. Rev. Lett. 100(14), 144103 (2008)
Marques, A.M., Lima, G.T.: Testing for Granger causality in quantiles between the wage share in income and productive capacity utilization. Structural Change and Economic Dynamics (2022)
McLemore, P., Mihov, A., Sanz, L.: Global banks and systemic risk: the dark side of country financial connectedness. J. Int. Money Financ. 129, 102734 (2022)
Rosoł, M., Młyńczak, M., Cybulski, G.: Granger causality test with nonlinear neural-network-based methods: Python package and simulation study. Comput. Methods Programs Biomed. 216, 106669 (2022)
Shojaie, A., Fox, E.B.: Granger causality: a review and recent advances. Annual Rev. Stat. Appl. 9, 289–319 (2022)
Tang, Y., Xiong, J.J., Luo, Y., Zhang, Y.C.: How do the global stock markets influence one another? evidence from finance big data and Granger causality directed network. Int. J. Electron. Commer. 23(1), 85–109 (2019)
Tank, A., Covert, I., Foti, N., Shojaie, A., Fox, E.B.: Neural Granger causality. IEEE Trans. Pattern Anal. Mach. Intell. 44(8), 4267–4279 (2021)
Wolpert, D.H.: Stacked generalization. Neural Networks 5(2), 241–259 (1992)
Zheng, Q., Song, L.: Dynamic contagion of systemic risks on global main equity markets based on Granger causality networks. Discrete Dynamics in Nature and Society 2018 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lu, Y. et al. (2023). Interpretability Meets Generalizability: A Hybrid Machine Learning System to Identify Nonlinear Granger Causality in Global Stock Indices. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13936. Springer, Cham. https://doi.org/10.1007/978-3-031-33377-4_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-33377-4_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33376-7
Online ISBN: 978-3-031-33377-4
eBook Packages: Computer ScienceComputer Science (R0)