The changing economic environment is fraught with uncertainty, making the prevention and resolution of financial risks and the enhancement of liquidity management capabilities key focuses and challenges for financial institutions and regulatory authorities in China. With the support of artificial intelligence and big data technologies, the research paradigms for liquidity risk management have been continuously enriched. Machine learning models have been proven to possess unique advantages in the field of liquidity risk identification. This paper summarizes the main application frameworks of machine learning in current risk management research, along with their applicability and limitations. It further explores potential future improvements and research trends in applying machine learning to identify liquidity risks.

Qianyi Chen, Xin Song. Based on Machine Learning: Research on Improving the Liquidity Risk Identification Model of Commercial Banks. Academic Journal of Business & Management(2025), Vol. 7, Issue 4: 98-103. https://doi.org/10.25236/AJBM.2025.070412.

[1] Dong Xiaolin, Wu Zhiwei, Chen Qiuyue. The Impact of Financial Technology Development on Risk Prevention and Control in Commercial Banks—An Empirical Analysis Based on 176 Commercial Banks in China [J]. Jiangsu Social Sciences, 2023, (01): 84-94+242-243.(In Chinese)

[2] Lee Chenying. Research on the Identification and Early Warning of Systemic Risks in China's Commercial Banks [J]. Journal of Central University of Finance & Economics, 2020, (10): 36-53.(In Chinese)

[3] Lee Shuang, Liu Yaya, Lee Xiaotong. Risk Monitoring and Early Warning of P2P Lending Platforms Based on Machine Learning [J]. Journal of Xi'an University of Finance and Economics, 2022, 35(02): 62-73.(In Chinese)

[4] Zhang Zongxin, Zhou Cong. Research on Early Warning of Credit Bond Liquidity Risk Based on Machine Learning [J]. International Finance Research, 2024, (05): 74-85.(In Chinese)

[5] Ni Xuanming, Zheng Tiantian, Zhao Huimin. Can Civil-Military Integration Reduce the Equity Financing Costs of High-Tech Enterprises?—An Empirical Study Based on Double Machine Learning [J]. Systems Engineering—Theory & Practice, 2023, 43(06): 1630-1650.(In Chinese)

[6] Dai Yarong, Shen Yifeng. Can Random Forest Models Predict Bond Defaults in China? [J]. Journal of Econometrics, 2022, 2(02): 418-440.(In Chinese)

[7] Lu Zhe, Zhang Jian. Credit Risk Prediction of Listed Companies Based on SMOTETomek-RFE-MLP Algorithm [J]. Systems Science and Mathematics, 2022, 42(10): 2712-2726.(In Chinese)

[8] Zhu Y, Sun B, et al. Predicting China’s SME Credit Risk in Supply Chain Financing by Logistic Regression, Artificial Neural Network and Hybrid Models[J]. Sustainability, 2016, 8(5): 433.

[9] Cui Yanyan, Liu Lixin. Risk Evaluation of P2P Lending Platforms Based on Big Data [J]. Statistics & Information Forum, 2020, 35(04): 42-51.(In Chinese)

[10] Shi Rong, Zhang Te, Yang Guotao. Machine Learning Methods in Econometrics: Review and Prospects [J]. Statistics & Decision, 2024, 40(01): 52-56.(In Chinese)

[11] Tavana M., Abtahi A. R., Di Caprio D., et al. An Artificial Neural Network and Bayesian Network Model for Liquidity Risk Assessment in Banking [J]. Neurocomputing, 2018, 275: 2525-2554.

[12] Triepels R., Daniels H., Berndsen R. Monitoring Liquidity Management of Banks with Recurrent Neural Networks [J]. Computational Economics, 2021, 57(1): 89-112.

[13] Yang Junqi, Ren Rui, Kan Lina, et al. Research on Risk Assessment of Commercial Banks Based on BP Neural Network Model [J]. Friends of Accounting, 2021, (05): 113-119.(In Chinese)

[14] Tan Benyan, Gan Ziqi. Measurement and Early Warning of Commercial Bank Liquidity Risk Based on BO-LightGBM [J]. Wuhan Finance, 2022, (11): 21-32.(In Chinese)

[15] Sumi K V. Neural network-based liquidity risk prediction in Indian private banks[J]. Intelligent Systems with Applications, 2024, 21: 200322.