Prediction of systemic risk of China’s financial industry based on phase space reconstruction and machine learning

i

This article has been updated. A Correction to this article was published on .

i

The Original Article was published on

i

The Original Article was published on

i

This article has been updated

i

This article was retracted on

i

This article has been updated

Abstract

Forecasting systemic financial risks is crucial for effectively preventing and mitigating such risks. This paper introduces an integrated framework for systemic financial risk forecasting, with its core innovation being the novel combination of phase space reconstruction with delay parameterization (RDPM) and a radial basis function neural network (RBFNN). Based on stock trading data from 41 listed companies in the China A-share stock market, a complex financial network is constructed. The RDPM-RBFNN approach reconstructs the underlying dynamical system by embedding a univariate time series into a high-dimensional phase space, thereby offering distinct advantages in characterizing the nonlinear dynamics inherent in financial risk. Its principal merit lies in its interpretability: It enables the estimation of measures including the largest Lyapunov exponent and time delay parameters, which quantitatively capture the system’s chaotic properties and nonlinear evolutionary patterns. On the other hand, phase space reconstruction requires less data and exhibiting resilience to non-stationarity. It provides a rigorous framework for diagnosing chaotic dynamics in financial systems, thereby yielding deeper insights into the complex mechanisms governing risk propagation. Although banks typically carry higher leverage as primary lending institutions and are often assumed to be central to systemic risk, our findings show that in the current financial landscape of China, securities and insurance companies constitute the dominant sources of systemic risk, whereas banks show notable stability. This reversal of conventional risk hierarchies illustrates how systemic risk concentration shifts across financial subsectors along with developmental trajectories. The elevated risk contribution of securities and insurance firms during the sample period, driven by their rapid expansion and deepening network integration, calls for a differentiated, activity-based approach to monitoring, with particular emphasis on systemically significant non-bank financial intermediaries. We think that the proposed framework in this paper is transferable to a broad spectrum of financial and economic systems and can be extended to model systemic interdependence in other complex adaptive systems.

Keywords

systemic financial risk / forecast / phase space reconstruction / delay parameterization method / machine learning

CHANGE HISTORY

A Correction to this paper has been published:
https://doi.org

The Retraction Note was updated to reflect reception of statements of disagreement from all authors.

This article has been retracted.Please see the Retraction Notice for more detail:
https://doi.org

References

[1] W. Silva, H. Kimura, V. A. Sobreiro, An analysis of the literature on systemic financial risk: A survey, J. Financ. Stab., 17(2017), 91-114. https://doi.org/10.1016/j.jfs.2016.12.004

[2] K. Bluwstein, M. Buckmann, A. Joseph, S. Kapadia, Ö. Şimşek, Credit growth, the yield curve and financial crisis prediction: Evidence from a machine learning approach, J. Int. Econ., 145(2023), 103773. https://doi.org/10.1016/j.jinteco.2023.103773

[3] S. Zedda, G. Cannas, Analysis of banks’ systemic risk contribution and contagion determinants through the leave-one-out approach, J. Banking Finance, 112(2020), 105160. https://doi.org/10.1016/j.jbankfin.2017.06.008

[4] G. Hale, T. Kapan, C. Minoiu, Shock transmission through cross-border bank lending: Credit and real effects, Rev. Financ. Stud., 33(2020), 4839-4882. https://doi.org/10.1093/rfs/hhz147

[5] M. V. Oordt, C. Zhou, Systemic risk and bank business models, J. Appl. Econom., 34(2019), 365-384. https://doi.org/10.1002/jae.2666

[6] V. Elenev, T. Landvoigt, S. V. Nieuwerburgh, A macroeconomic model with financially constrained producers and intermediaries, Econometrica, 89(2021), 1361-1418. https://doi.org/10.3982/ECTA16438

[7] S. Benoit, J. E. Colliard, C. Hurlin, C. Pérignon, Where the risks lie: A survey on systemic risk, Rev. Finance, 21(2017), 109-152. https://doi.org/10.1093/rof/rfw026

[8] C. Diks, C. Hommes, J. Wang, Critical slowing down as an early warning signal for financial crises, Empir. Econ., 57(2019), 1201-1228. https://doi.org/10.1007/s00181-018-1527-3

[9] M. Summer, Financial contagion and network analysis, Annu. Rev. Financ. Econ., 5(2013), 277-297. https://doi.org/10.1146/annurev-financial-110112-120948

[10] Z. Du, J. C. Escanciano, Backtesting expected shortfall: Accounting for tail risk, Manage. Sci., 63(2017), 940-958. https://doi.org/10.1287/mnsc.2015.2342

[11] V. V. Acharya, L. H. Pedersen, T. Philippon, M. Richardson, Measuring systemic risk, Rev. Financ. Stud., 30(2017), 2-47. https://doi.org/10.1093/rfs/hhw088

[12] T. Adrian, M. K. Brunnermeier, CoVaR, Am. Econ. Rev., 106(2016), 1705-1741. http://dx.doi.org/10.1257/aer.20120555

[13] E. Grant, J. Yung, The double-edged sword of global integration: Robustness, fragility, and contagion in the international firm network, J. Appl. Econom., 36(2021), 760-783. https://doi.org/10.1002/jae.2839

[14] M. Billio, M. Getmansky, A. W. Lo, L. Pelizzon, Econometric measures of connectedness and systemic risk in the finance and insurance sectors, J. Financ. Econ., 104(2012), 535-559. https://doi.org/10.1016/j.jfineco.2011.12.010

[15] G. Bostanci, K. Yilmaz, How connected is the global sovereign credit risk network, J. Bank. Finance, 113(2020), 105761. https://doi.org/10.1016/j.jbankfin.2020.105761

[16] G. J. Wang, L. Wan, Y. Feng, C. Xie, G. S. Uddin, Y. Zhu, Interconnected multilayer networks: Quantifying connectedness among global stock and foreign exchange markets, Int. Rev. Financ. Anal., 86(2023), 102518. https://doi.org/10.1016/j.irfa.2023.102518

[17] Z. Ouyang, X. Zhou, Multilayer networks in the frequency domain: Measuring extreme risk connectedness of Chinese financial institutions, Res. Int. Bus. Finance, 65(2023), 101944. https://doi.org/10.1016/j.ribaf.2023.101944

[18] Ö. Akgüller, M. A. Balcı, Detecting financial contagion through higher-order networks: A deep learning approach to emerging market risk, Comput. Econ., (2026), 1-67. https://doi.org/10.1007/s10614-025-11287-3

[19] F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, G. Monfardini, The graph neural network model, IEEE Trans. Neural Networks, 20(2009), 61-80. https://doi.org/10.1109/TNN.2008.2005605

[20] D. Parnes, A. Gormus, Prescreening bank failures with K-means clustering: Pros and cons, Int. Rev. Financ. Anal., 93(2024), 103222. https://doi.org/10.1016/j.irfa.2024.103222

[21] K. K. Sharma, A. Seal, Spectral embedded generalized mean based k-nearest neighbors clustering with s-distance, Expert Syst. Appl., 169(2021), 114326. https://doi.org/10.1016/j.eswa.2020.114326

[22] A. R. Benson, D. F. Gleich, J. Leskovec, Higher-order organization of complex networks, Science, 353(2016), 163-166. https://doi.org/10.1126/science.aad9029

[23] J. Duffy, A. Karadimitropoulou, M. Parravano, Financial contagion in the laboratory: Does network structure matter, J. Money Credit Bank., 51(2019), 1097-1136. https://doi.org/10.1111/jmcb.12563

[24] C. Filippopoulou, E. Galariotis, S. Spyrou, An early warning system for predicting systemic banking crises in the Eurozone: A logit regression approach, J. Econ. Behav. Organ., 172(2020), 344-363. https://doi.org/10.1016/j.jebo.2019.12.023

[25] Z. Gu, Y. Xu, Chaotic dynamics analysis based on financial time series, Complexity, (2021), 2373423. https://doi.org/10.1155/2021/2373423

[26] M. Pirani, P. Thakka, P. Jivrani, M. H. Bohara, D. Garg, A comparative analysis of ARIMA, GRU, LSTM and BiLSTM on financial time series forecasting, in 2022 IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE), Ballari, India, 2022, 1-6. https://doi.org/10.1109/ICDCECE53908.2022.9793213

[27] N. Nazareth, Y. V. R. Reddy, Financial applications of machine learning: A literature review, Expert Syst. Appl., (2023) 119640. https://doi.org/10.1016/j.eswa.2023.119640

[28] S. Ahmed, M. M. Alshater, A. El Ammari, H. Hammami, Artificial intelligence and machine learning in finance: A bibliometric review, Res. Int. Bus. Finance, 61(2022), 101646. https://doi.org/10.1016/j.ribaf.2022.101646

[29] G. Kou, X. Chao, Y. Peng, F. E. Alsaadi, E. Herrera-Viedma, Machine learning methods for systemic risk analysis in financial sectors, Technol. Econ. Dev. Econ., 25(2019), 716-742. https://doi.org/10.3846/tede.2019.8740

[30] J. Beutel, S. List, G. von Schweinitz, Does machine learning help us predict banking crises, J. Financ. Stab., 45(2019), 100693. https://doi.org/10.1016/j.jfs.2019.100693

[31] V. Balmaseda, M. Coronado, G. C. Santiago, Predicting systemic risk in financial systems using Deep Graph Learning, Intell. Syst., (2023), 200240. https://doi.org/10.1016/j.iswa.2023.200240

[32] T. Leonidas, T. Alexandra, B. Aristeidis, Big data in financial risk management: Evidence, advances, and open questions: A systematic review, Front. Artif. Intell., 8(2025), 1658375. https://doi.org/10.3389/frai.2025.1658375

[33] L. J. Vásquez-Serpa, C. Rodríguez, J. R. Pérez-Núñez, C. Navarro, Challenges of Artificial Intelligence for the prevention and identification of bankruptcy risk in financial institutions: A systematic review, J. Risk Financ. Manage., 18(2025), 26. https://doi.org/10.3390/jrfm18010026

[34] A. Wolf, J. B. Swift, H. L. Swinney, J. A. Vastano, Determining Lyapunov exponents from a time series, Phys. D: Nonlinear Phenom., 16(1985), 285-317. https://doi.org/10.1016/0167-2789(85)90011-9

[35] M. D. Johansyah, S. Vaidyanathan, K. Benkouider, A. Sambas, C. Aruna, S. K. Annavarapu, et al., A chaotic butterfly attractor model for economic stability assessment in financial systems, Mathematics, 13(2025), 1633. https://doi.org/10.3390/math13101633

[36] K. He, J. Shi, H. Fang, Bifurcation and chaos analysis of a fractional-order delay financial risk system using dynamic system approach and persistent homology, Math. Comput. Simul., 223(2024), 253-274. https://doi.org/10.1016/j.matcom.2024.04.013

[37] X. Yan, H. Wang, Y. An, Forecasting systemic risk of China’s banking industry by PDE model, J. Appl. Anal. Comput., 13(2023), 1-27. https://doi.org/10.11948/20230306

[38] L. Yang, T. Gao, Y. Lu, J. Duan, T. Liu, Neural network stochastic differential equation models with applications to financial data forecasting, Appl. Math. Model., 115(2023), 279-299. https://doi.org/10.1016/j.apm.2022.11.001

[39] W. Sun, Y. An, Y. Gao, Systemic risk contagion in China’s financial-real estate network: Modeling and forecasting via fractional order PDEs, Fractal Fract., 9(2025), 557. https://doi.org/10.3390/fractalfract9090557

[40] X. Guo, W. Han, J. Ren, Design of a prediction system based on the dynamical feed-forward neural network, Sci. China Inf. Sci., 66(2023), 1-17. https://doi.org/10.1007/s11432-020-3402-9

[41] X. Guo, Y. Sun, J. Ren, Low dimensional mid-term chaotic time series prediction by delay parameterized method, Inf. Sci., 516(2020), 1-19. https://doi.org/10.1016/j.ins.2019.12.021

[42] A. Zhang, Z. Xu, Chaotic time series prediction using phase space reconstruction based conceptor network, Cogn. Neurodyn., 14(2020), 849-857. https://doi.org/10.1007/s11571-020-09612-7

[43] H. Ma, S. Leng, K. Aihara, L. Chen, Randomly distributed embedding making short-term high-dimensional data predictable, Proc. Natl. Acad. Sci. U.S.A., 115(2018), E9994-E10002. https://doi.org/10.1073/pnas.1802987115

[44] C. Chen, R. Li, L. Shu, Z. He, J. Wang, C. Zhang, et al., Predicting future dynamics from short-term time series using an Anticipated Learning Machine, Natl. Sci. Rev., 7(2020), 1079-1091. https://doi.org/10.1093/nsr/nwaa025

[45] J. Hou, H. Ma, D. He, J. Sun, Q. Nie, W. Lin, Harvesting random embedding for high-frequency change-point detection in temporal complex systems, Natl. Sci. Rev., 9(2022), 92-104. https://doi.org/10.1093/nsr/nwab228

[46] M. Lan, Energy control and chaos prediction of a fractional-order financial risk contagion system, Phys. Scr., 100(2025), 085240. https://doi.org/10.1088/1402-4896/adf3ee

[47] Y. Wang, M. F. Ghazali, R. A. Razak, M. A. S. Zaidi, Complex system and PS-LSTM prediction of cryptocurrencies, stocks, bonds, exchange rates and commodities, Phys. A: Stat. Mech. Appl., (2025), 130976. https://doi.org/10.1016/j.physa.2025.130976

[48] M. S. Murugan, Large-scale data-driven financial risk management & analysis using machine learning strategies, Meas.: Sens., 27(2023), 100756. https://doi.org/10.1016/j.measen.2023.100756

[49] X. Fan, Y. Wang, D. Wang, Network connectedness and China’s systemic financial risk contagion analysis based on big data, Pac. Basin Finance J., 68(2021), 101322. https://doi.org/10.1016/j.pacfin.2020.101322

[50] P. Song, Y. Xiao, Estimating time-varying reproduction number by deep learning techniques, J. Appl. Anal. Comput., 12(2022), 1077-1089. https://doi.org/10.11948/20220136

[51] H. Hu, L. Tang, S. Zhang, H. Wang, Predicting the direction of stock markets using optimized neural networks with Google trends, Neurocomputing, 285(2018), 188-195. https://doi.org/10.1016/j.neucom.2018.01.038

[52] I. Choi, W. C. Kim, Practical forecasting of risk boundaries for industrial metals and critical minerals via statistical machine learning techniques, Int. Rev. Financ. Anal., 94(2024), 103252. https://doi.org/10.1016/j.irfa.2024.103252

[53] F. Takens, Detecting strange attractors in turbulence, Dyn. Syst. Turbul., 344(1981), 366-381. https://doi.org/10.1007/BFb0091924

[54] E. R. Deyle, G. Sugihara, Generalized theorems for nonlinear state space reconstruction, PLoS ONE, 6(2011), 18295. https://doi.org/10.1371/journal.pone.0018295

[55] L. C. Zheng, X. Q. Huang, X. Y. Lu, Nonbank financial institutions and financial stability: Time series analysis, Financ. Res. Lett., 73(2025), 106544. https://doi.org/10.1016/j.frl.2024.106544

[56] Y. Gao, R. Tan, C. Fu, S. Cai, Revealing stock market risk from information flow based on transfer entropy: The case of Chinese A-shares, Phys. A: Stat. Mech. Appl., (2023), 128982. https://doi.org/10.1016/j.physa.2023.128982

[57] L. Barnett, A. B. Barrett, A. K. Seth, Granger causality and transfer entropy are equivalent for Gaussian variables, Phys. Rev. Lett., 103(2009), 238701. https://doi.org/10.1103/PhysRevLett.103.238701

[58] S. Thomas, Measuring information transfer, Phys. Rev. Lett., 85(2000), 461. https://doi.org/10.1103/PhysRevLett.85.461

[59] I. Choi, W. C. Kim, A temporal information transfer network approach considering federal funds rate for an interpretable asset fluctuation prediction framework, Int. Rev. Econ. Finance, 96(2024), 103562. https://doi.org/10.1016/j.iref.2024.103562

[60] S. Battiston, M. Puliga, R. Kaushik, P. Tasca, G. Caldarelli, DebtRank: Too central to fail? Financial networks, the FED and systemic risk, Sci. Rep., 2(2012), 541. https://doi.org/10.1038/srep00541

[61] J. Sánchez García, S. Cruz Rambaud, Systemic risk in a macro-multiplex network, Soft Comput., 30(2026), 1839-1851. https://doi.org/10.1007/s00500-023-09460-7

[62] F. X. Diebold, K. Yilmaz, On the network topology of variance decompositions: Measuring the connectedness of financial firms, J. Econom., 182(2014), 119-134. https://doi.org/10.1016/j.jeconom.2014.04.012

[63] H. Tzavellas, A multilayer view of systemic importance and aggregate fluctuations, Int. Econ. Rev., 64(2023), 1023-1046. https://doi.org/10.1111/iere.12622

[64] D. Caldara, M. Iacoviello, Measuring geopolitical risk, Am. Econ. Rev., 112(2022), 1194-1225. https://doi.org/10.1257/aer.20191823