Author(s)

Yunpeng Zhao ¹

Affiliation(s)

¹ Treasury Department, Bank of China, New York, NY 10018, USA

Corresponding Author

Yunpeng Zhao

ABSTRACT

This study focuses on the liquidity risk management of credit debt, aiming to explore effective measurement and early warning methods to reduce the potential threat of systemic financial risks to security. This study by analysing the monthly data of China's credit debt from January 2009 to December 2020, this paper evaluates the liquidity risk of credit debt using tail correlation, and constructs an early warning factor system from three perspectives: financing constraints, credit risk and noise trading. Furthermore, 11 kinds of machine learning models, including neural networks, are used for early warning analysis of credit debt liquidity risk. The results show that the neural network with a hidden layer shows high warning accuracy under various bonds and different environmental conditions, especially can effectively capture the market liquidity crunch signal. The maturity of bonds has a significant impact on liquidity risk. Newly issued bonds face higher risk due to noisy trading. With the increase of maturity, this risk gradually decreases, but the weakening speed tends to be gentle. It is also found that the formation of liquidity risk is closely related to the synergistic effect of multiple risk factors, especially the nonlinear interaction between economic situation, monetary policy changes, cross-market shocks and bond age, which plays an important role in promoting the evolution of liquidity risk. This study deepens the understanding of credit debt liquidity risk and provides a new theoretical basis for risk management practice.

KEYWORDS

Credit Debt, Liquidity Risk, Tail Correlation, Risk Factor System, Neural Network, Machine Learning Model, Risk Measurement, Risk Warning, Noise Trading, Maturity Impact

CITE THIS PAPER

Yunpeng Zhao, Research on Credit Debt Liquidity Risk Measurement and Early Warning Based on Machine Learning Model. Information Systems and Economics (2024) Vol. 5: 18-23. DOI: http://dx.doi.org/10.23977/infse.2024.050503.

REFERENCES

[1] Chen H, Yang Y, & Shao C. Multi-task learning for data-efficient spatiotemporal modeling of tool surface progression in ultrasonic metal welding [J]. Journal of Manufacturing Systems, 2021, 58, 306-315.
[2] Varatharajah Y, Chen H, Trotter A, & Iyer R K. A Dynamic Human-in-the-loop Recommender System for Evidence-based Clinical Staging of COVID-19 [J]. In HealthRecSys@ RecSys, 2020, 21-22 
[3] Zhang X, Zhao D, Ma Y, et al. Research on high-precision angular measurement based on machine learning and optical vortex interference technology [J]. IOP Publishing Ltd, 2024. DOI:10.1088/1361-6501/ad6207.
[4] Wei Z, Dong J, Dong Z. Research on Prediction and Early Warning of A-Share Market Volatility Based on HAR-Type Models [J]. Journal of Systems Science and Information, 2023, 11(6): 671-690.

Sponsors, Associates, and Links

---

• Accounting, Auditing and Finance
  
  
• Industrial Engineering and Innovation Management
  
  
• Tourism Management and Technology Economy
  
  
• Journal of Computational and Financial Econometrics
  
  
• Financial Engineering and Risk Management
  
  
• Accounting and Corporate Management
  
  
• Social Security and Administration Management
  
  
• Population, Resources & Environmental Economics
  
  
• Statistics & Quantitative Economics
  
  
• Agricultural & Forestry Economics and Management
  
  
• Social Medicine and Health Management
  
  
• Land Resource Management
  
  
• Information, Library and Archival Science
  
  
• Journal of Human Resource Development
  
  
• Manufacturing and Service Operations Management
  
  
• Operational Research and Cybernetics