{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:38:24Z","timestamp":1760060304380,"version":"build-2065373602"},"reference-count":43,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100017630","name":"Humanities and Social Sciences Youth Foundation, Ministry of Education","doi-asserted-by":"publisher","award":["23YJCZH261","NYY222024"],"award-info":[{"award-number":["23YJCZH261","NYY222024"]}],"id":[{"id":"10.13039\/501100017630","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Startup Foundation for Introducing Talent of Nanjing University of Posts and Telecommunications","award":["23YJCZH261","NYY222024"],"award-info":[{"award-number":["23YJCZH261","NYY222024"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>With the accelerated development of economic globalization, it is of great significance to strengthen the ability to measure, evaluate, and warn of systemic financial risks for preventing and defusing financial risks. Thus, this research established the Time-Varying Parameter Factor-Augmented Vector Autoregression model (TVP-FAVAR), combined with the Markov Regime Switching Autoregressive Model, to dynamically measure China\u2019s systemic financial risk. The network public opinion index is constructed and introduced into the financial risk early warning system to capture the dynamic impact of market sentiment on financial risks. After testing the nonlinear causal relationship between financial indicators based on the transfer entropy method, the Transformer deep learning model is applied to build a financial risk early warning system, and the performance is compared to traditional methods. The experimental results showed that (1) the trend of the systemic financial risk index based on the dynamic measurement of the TVP-FAVAR model fitted the actual situation well and that (2) the Transformer model public opinion index could fully and effectively mine the nonlinear relationship between data. Compared to traditional machine learning methods, the Transformer model has significant advantages in stronger prediction accuracy and generalization ability. This study provided a new technical path for financial risk early warning and has important reference value for improving the financial regulatory system.<\/jats:p>","DOI":"10.3390\/systems13080720","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:02:44Z","timestamp":1755763364000},"page":"720","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on Dynamic Measurement and Early Warning of Systemic Financial Risk in China Based on TVP-FAVAR and Deep Learning Model"],"prefix":"10.3390","volume":"13","author":[{"given":"Hufang","family":"Yang","sequence":"first","affiliation":[{"name":"School of Economics, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luyi","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Economics, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jieyang","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Economics, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3414-2144","authenticated-orcid":false,"given":"Wenbin","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Economics, Nanjing University of Finance & Economics, Nanjing 210023, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"ref_1","first-page":"185","article-title":"A Literature Review of Systemic Risk: Status, Development and Prospect","volume":"1","author":"Yang","year":"2022","journal-title":"J. Financ. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.1257\/aer.20120555","article-title":"CoVaR","volume":"106","author":"Tobias","year":"2016","journal-title":"Am. Econ. Rev."},{"key":"ref_3","first-page":"267","article-title":"Volatility of the Returns and Expected Losses of Islamic Bank Financing","volume":"3","author":"Ismal","year":"2010","journal-title":"Int. J. Islam. Middle East. Financ. Manag."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1016\/j.jbankfin.2004.08.010","article-title":"Value-at-Risk versus Expected Shortfall: A Practical Perspective","volume":"29","author":"Yamai","year":"2005","journal-title":"J. Bank. Financ."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"124065","DOI":"10.1016\/j.jenvman.2025.124065","article-title":"Nonlinear Relationship between Physical Environment Risks, Investor Attentions, and Financial Systemic Risks: Evidence from MLSTM-CoVaR Networks","volume":"374","author":"Wang","year":"2025","journal-title":"J. Environ. Manag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.1016\/S0378-4266(02)00283-2","article-title":"On the Coherence of Expected Shortfall","volume":"26","author":"Acerbi","year":"2002","journal-title":"J. Bank. Financ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1080\/14697688.2024.2352542","article-title":"Risk Management under Weighted Limited Expected Loss","volume":"24","author":"Chen","year":"2024","journal-title":"Quant. Financ."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1093\/rfs\/hhw088","article-title":"Measuring Systemic Risk","volume":"30","author":"Acharya","year":"2017","journal-title":"Rev. Financ. Stud."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"100920","DOI":"10.1016\/j.jfi.2021.100920","article-title":"The External Effects of Bank Executive Pay: Liquidity Creation and Systemic Risk","volume":"47","author":"DeYoung","year":"2021","journal-title":"J. Financ. Intermediat."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3107","DOI":"10.1016\/j.csda.2007.09.025","article-title":"A Bayesian Approach to Estimate the Marginal Loss Distributions in Operational Risk Management","volume":"52","author":"Giudici","year":"2008","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_11","first-page":"365","article-title":"Measures of Financial Stability-a Review","volume":"31","author":"Gadanecz","year":"2008","journal-title":"Irving Fish. Comm. Bull."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1146\/annurev-financial-110311-101754","article-title":"A Survey of Systemic Risk Analytics","volume":"4","author":"Bisias","year":"2012","journal-title":"Annu. Rev. Financ. Econ."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1515\/jcbtp-2016-0006","article-title":"Financial Stability Indicators\u2014The Case of Croatia","volume":"5","year":"2016","journal-title":"J. Cent. Bank. Theory Pract."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.jfineco.2016.01.010","article-title":"Systemic Risk and the Macroeconomy: An Empirical Evaluation","volume":"119","author":"Giglio","year":"2016","journal-title":"J. Financ. Econ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102913","DOI":"10.1016\/j.irfa.2023.102913","article-title":"Measurement and Contagion Modelling of Systemic Risk in China\u2019s Financial Sectors: Evidence for Functional Data Analysis and Complex Network","volume":"90","author":"Tian","year":"2023","journal-title":"Int. Rev. Financ. Anal."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1093\/rof\/rfw026","article-title":"Where the Risks Lie: A Survey on Systemic Risk","volume":"21","author":"Benoit","year":"2017","journal-title":"Rev. Financ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"102258","DOI":"10.1016\/j.najef.2024.102258","article-title":"Network Measurement and Influence Mechanism of Dynamic Risk Contagion among Global Stock Markets: Based on Time-Varying Spillover Index and Complex Network Method","volume":"74","author":"Yu","year":"2024","journal-title":"N. Am. J. Econ. Financ."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"108301","DOI":"10.1016\/j.eneco.2025.108301","article-title":"Dynamic Risk Spillover in Green Financial Markets: A Wavelet Frequency Analysis from China","volume":"143","author":"Wang","year":"2025","journal-title":"Energy Econ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"113065","DOI":"10.1016\/j.cam.2020.113065","article-title":"Applying Deep Learning Method in TVP-VAR Model under Systematic Financial Risk Monitoring and Early Warning","volume":"382","author":"Huang","year":"2021","journal-title":"J. Comput. Appl. Math."},{"key":"ref_20","first-page":"327","article-title":"Research on Financial Risk Early Warning System Model Based on Second-Order Blockchain Differential Equation","volume":"18","author":"Li","year":"2024","journal-title":"Intell. Decis. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1016\/j.aasri.2012.06.067","article-title":"The Research of the Regional Financial Risk Early-Warning Model Integrating the Regression of Lagging Factors","volume":"1","author":"Zhu","year":"2012","journal-title":"AASRI Procedia"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2300","DOI":"10.1016\/j.egyr.2022.12.151","article-title":"Energy Financial Risk Early Warning Model Based on Bayesian Network","volume":"9","author":"Wei","year":"2023","journal-title":"Energy Rep."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"102944","DOI":"10.1016\/j.ribaf.2025.102944","article-title":"Hierarchical Clustering-Based Early Warning Model for Predicting Bank Failures: Insights from Ghana\u2019s Financial Sector Reforms (2017\u20132019)","volume":"77","author":"Owoo","year":"2025","journal-title":"Res. Int. Bus. Financ."},{"key":"ref_24","first-page":"1","article-title":"Measurement and Early Warning of Systemic Financial Risk in China: Markov Switching Models","volume":"65","author":"Wang","year":"2025","journal-title":"Comput. Econ."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"100898","DOI":"10.1016\/j.gfj.2023.100898","article-title":"Research on the FinTech Risk Early Warning Based on the MS-VAR Model: An Empirical Analysis in China","volume":"58","author":"Bu","year":"2023","journal-title":"Glob. Financ. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"111445","DOI":"10.1016\/j.econlet.2023.111445","article-title":"Dynamic Monitoring of Financial Security Risks: A Novel China Financial Risk Index and an Early Warning System","volume":"234","author":"Zhang","year":"2024","journal-title":"Econ. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1111\/sjoe.12216","article-title":"Predicting Banking Crises with Artificial Neural Networks: The Role of Nonlinearity and Heterogeneity","volume":"120","author":"Ristolainen","year":"2018","journal-title":"Scand. J. Econ."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"103773","DOI":"10.1016\/j.jinteco.2023.103773","article-title":"Credit Growth, the Yield Curve and Financial Crisis Prediction: Evidence from a Machine Learning Approach","volume":"145","author":"Bluwstein","year":"2023","journal-title":"J. Int. Econ."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"127746","DOI":"10.1016\/j.eswa.2025.127746","article-title":"Deep Learning-Based Financial Risk Early Warning Model for Listed Companies: A Multi-Dimensional Analysis Approach","volume":"283","author":"Chen","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"101383","DOI":"10.1016\/j.najef.2021.101383","article-title":"Systemic Financial Risk Early Warning of Financial Market in China Using Attention-LSTM Model","volume":"56","author":"Ouyang","year":"2021","journal-title":"N. Am. J. Econ. Financ."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"102151","DOI":"10.1016\/j.najef.2024.102151","article-title":"Network-Based Prediction of Financial Cross-Sector Risk Spillover in China: A Deep Learning Approach","volume":"72","author":"Tang","year":"2024","journal-title":"N. Am. J. Econ. Financ."},{"key":"ref_32","first-page":"1","article-title":"Attention Is All You Need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_33","first-page":"387","article-title":"Measuring the Effects of Monetary Policy: A Factor-Augmented Vector Autoregressive (FAVAR) Approach","volume":"120","author":"Bernanke","year":"2005","journal-title":"Q. J. Econ."},{"key":"ref_34","unstructured":"Agrrawal, P., and Clark, J.M. (,  2009). A multivariate liquidity score and ranking device for ETFs. Proceedings of the Academy of Financial Services Annual Conference, Boca Raton, FL, USA. Available online: https:\/\/www.researchgate.net\/publication\/257890697_A_Multivariate_Liquidity_Score_and_Ranking_Device_for_ETFs."},{"key":"ref_35","first-page":"53","article-title":"Interaction between Value Line\u2019s timeliness and safety ranks","volume":"10","author":"Waggle","year":"2001","journal-title":"J. Investig."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Valadkhani, A. (2025). Inflation-driven instability in US sectoral betas. J. Asset Manag., 1\u20138.","DOI":"10.1057\/s41260-025-00413-3"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2513","DOI":"10.1016\/j.cor.2004.03.016","article-title":"Forecasting stock market movement direction with support vector machine","volume":"32","author":"Huang","year":"2005","journal-title":"Comput. Oper. Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"4627","DOI":"10.5194\/amt-11-4627-2018","article-title":"A neural network approach to estimating a posteriori distributions of Bayesian retrieval problems","volume":"11","author":"Pfreundschuh","year":"2018","journal-title":"Atmos. Meas. Technol."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wang, J., Xu, Y., Liu, L., Wu, W., Shen, C., Huang, H., Zhen, Z., Meng, J., Li, C., and Qu, Z. (2023). Comparison of LASSO and random forest models for predicting the risk of premature coronary artery disease. BMC Med. Inform. Decis. Mak., 23.","DOI":"10.1186\/s12911-023-02407-w"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Coelho e Silva, L., Fonseca, G.F., and Castro, P.A.L. (2024, January 14\u201317). Transformers and attention-based networks in quantitative trading: A comprehensive survey. Proceedings of the 5th ACM International Conference on AI in Finance, New York, NY, USA.","DOI":"10.1145\/3677052.3698684"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., and Wolf, L. (2021, January 20\u201325). Transformer interpretability beyond attention visualization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Kim, Y.S., and Kwon, O. (2019, February 08). Central Bank Digital Currency and Financial Stability. Bank of Korea WP 2019-6. Available online: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=3330914.","DOI":"10.2139\/ssrn.3330914"}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/8\/720\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:32:21Z","timestamp":1760034741000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/13\/8\/720"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":43,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["systems13080720"],"URL":"https:\/\/doi.org\/10.3390\/systems13080720","relation":{},"ISSN":["2079-8954"],"issn-type":[{"type":"electronic","value":"2079-8954"}],"subject":[],"published":{"date-parts":[[2025,8,21]]}}}