Analysis of Regional Financial Risk Factors under Random Forest
DOI:
https://doi.org/10.54097/j2eaqf60Keywords:
Random forest model, Entropy weight method, Regional financial risks, regional heterogeneity.Abstract
Objectively understanding the current state of China's financial risks and their external drivers is a crucial guarantee for maintaining financial security and stability, and promoting high-quality financial development. This paper breaks through the limitations of traditional indicators in monitoring shadow banking, cross-border capital, and the marginal effects of debt risk. It employs the entropy weight method to construct a comprehensive regional risk assessment framework covering four sectors, and empirically analyzes the main external influencing factors of regional financial risks based on the random forest model. The research indicates that: (1) China's regional financial risks exhibit significant spatial differentiation, with major influencing factors forming a four-tier risk driver system. (2) The risk sources in different strategic regions stem from the reshaping of regional economic structures due to national strategic positioning. This is manifested in three regional dynamics: the Beijing-Tianjin-Hebei region demonstrates dual constraints through state-owned enterprises' dominance in major project investments; the Yangtze River Delta, as an export-oriented economic hub, exhibits heightened susceptibility to international market fluctuations; while the Yangtze River Economic Belt illustrates the critical equilibrium between large-scale infrastructure investment and local fiscal capacity in cross-regional coordination. (3) Regional risk governance needs to emphasize the asymmetry of dynamic evolution, providing a scientific basis for differentiated policy measures.
Downloads
References
[1] CAO Y, CAI Z. The Empirical Analysis on the Contagion Effect of the Regional Financial Risks Based on the VAR Model -- Illustrated by the Data Before and After the International Financial Crisis [J]. On Economic Problems, 2013, (10): 59 - 64.
[2] D’Amico, G., Basilio, B.D. and Petroni, F. Drawdown-based risk indicators for high-frequency financial volumes [J]. Financial Innovation, 2024, 10 (1).
[3] GIUDICI P, SARLIN P, SPELTA A. The interconnected nature of financial systems: direct and common exposures [J]. Journal of Banking & Finance, 2020, 112: 105149.
[4] Kim, K. Liquidity basis between credit default swaps and corporate bonds markets [J]. International Review of Economics & Finance, 2017, 48: 98 – 115.
[5] Lai, J., and Lyu, J. L. Measurement of Financial Systemic Risk Based on Financial Stress Index [J]. Statistics and Decision, 2010, (19): 128 - 131.
[6] Li, F. and Perez-Saiz, H. Measuring systemic risk across financial market infrastructures [J]. Journal of Financial Stability, 2018, 34: 1 – 11.
[7] Li, L. H., and Han, J. W. Does Financial Innovation Exacerbate Regional Financial Risk? --A Study Based on Social Network and Dynamic Panel Threshold Effects [J]. Securities Market Herald, 2023, (3): 68 - 79.
[8] Li, N. Measurement of Systemic Financial Risk Based on Real Estate Market [J]. Frontiers in Business, Economics and Management, 2024, 17 (3): 185 – 188.
[9] Li, Q. and YUSOFF, M.E. The Impact of Household Financial Asset Allocation on Regional Bank Risk Spillovers [J]. Proceedings of the International Conference on Information Economy, Data Modeling and Cloud Computing, ICIDC 2022, 17 - 19.
[10] Shen L, Liu Y, Li W. China's Regional Financial Risk Spatial Correlation Network and Regional Contagion Effect: 2009-2016 [J]. Management Review, 2019, 31 (8): 35 - 48.
[11] Shen, L., Zhang, Y., Li, W., and Liu, Y. Spatial-Temporal Evolution and Driving Mechanisms of Regional Financial Risks in China: A Perspective of Four Economic Sectors [J]. Southern Economic Journal, 2019, (9).
[12] Tang E, Bai C, Qin T. Digital finance and regional systemic financial risk Forecasting [J]. Applied Mathematics and Nonlinear Sciences, 2024, 9 (1).
[13] Xu Y. Empirical Study on the Measurement and Influencing Factors of China's Systemic Financial Risk Based on Machine Learning [J]. Financial Development Review, 2023, (10): 44 - 61.
[14] WANG, Z. A Study on Early Warning of Financial Indicators of Listed Companies Based on Random Forest [J]. Scientific Programming, 2022.
[15] YANGYUDONGNANXIN, G., ALI, R. Financial Credit Risk Control Strategy Based on Weighted Random Forest Algorithm [J]. Scientific Programming, 2021, (2).
[16] ZHANG L, ZHANG S. Progress on Machine Learning for Regional Financial Risk Prevention [J]. Journal of Frontiers of Computer Science and Technology, 2022, 16 (9): 1969 - 1989.
[17] ZHOU W, He Z. Study on spatial distribution, regional differences and dynamic evolution of rural financial risk in China [J]. PLOS ONE, 2024, 19 (5): e0301977.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Business, Economics and Management
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
