Construction and Comparative Analysis of Financial Risk Early Warning Model Based on Machine Learning_Vol. 2 No. 3 (JBDC 2024)_Journal of Big Data and Computing (ISSN: 2959-0590)

Home > Journal of Big Data and Computing (ISSN: 2959-0590) > Vol. 2 No. 3 (JBDC 2024) >

Construction and Comparative Analysis of Financial Risk Early Warning Model Based on Machine Learning

Download PDF

DOI: https://doi.org/10.62517/jbdc.202401325

Author(s)

Wu Xiannan

Affiliation(s)

Zhejiang Gongshang University Hangzhou College of Commerce, Zhejiang, China

Abstract

Amidst the progressing intensification of globalization and economic integration, the management of financial market volatility and risk has become a critical concern for businesses. The escalating complexity of financial crises has heightened the urgency for advanced early warning systems capable of accurately forecasting future risks. In this context, this study has developed a suite of financial risk early warning models leveraging machine learning techniques, encompassing Support Vector Machine (SVM), Random Forest (RF), and Deep Learning (DL) models, and conducted a thorough comparative analysis. The research utilized financial statement data and market transaction records from A-share listed companies spanning 2008 to 2022. Post the removal of multicollinearity, standardization, and outlier exclusion, a dataset was curated that included over 30 financial indicators such as the current ratio, debt-to-asset ratio, and net profit growth rate. A logistic regression model was applied for baseline comparison, revealing that machine learning models notably outperformed it across key metrics including accuracy, precision, and recall rates.The DL model, in particular, showcased enhanced predictive capabilities for financial risks, attributable to its proficiency in capturing non-linear features and its automated high-level feature extraction capabilities. Conversely, the RF model provided practical benefits in terms of feature interpretability, swift training, and the provision of feature importance scores. To bolster the models' adaptability and predictive accuracy in complex scenarios, the study proposes enhancements, advocating for an early warning mechanism within DL models that integrates multi-source heterogeneous data and dynamic financial indicators. Moreover, to address the dynamic nature of financial markets, this study has integrated a real-time assessment mechanism. This mechanism facilitates ongoing monitoring and prompt adjustment of model parameters in response to market fluctuations, ensuring the model's sustained efficacy and dependability. The generalizability of the models was substantiated through time-series cross-validation and replication across various industry subsamples, demonstrating their stability and robust performance. This research presents scientific financial risk assessment tools for corporate management and investors, laying the groundwork for future advancements in the domain.

Keywords

Financial Risk Early Warning; Machine Learning; Support Vector Machines; Random Forests; Deep Learning; Real-Time Assessment; Model Robustness

References

[1] Liu, M., Gao, R., & Fu, W. (2021). Analysis of Internet Financial Risk Control Model Based on Machine Learning Algorithms. Hindawi Journal of Mathematics, 2021: 8541929-1–8541929-10. [2] Xu, Z. H. (2021). Research on the Financial Risk Early Warning Model Based on Improved SMOTE (Master's Thesis, South China University of Technology). Master's Thesis. https://link-cnki-net-s.webvpn.zjhzcc.edu.cn/doi/10.27151/d.cnki.ghnlu.2021.002534 doi:10.27151/d.cnki.ghnlu.2021.002534. [3] Bo Yang & Xinfei Wang. (2019). Construction of Logistics Financial Risk Ontology Model Based on Risk Correlation. In Proceedings of 2019 International Conference on Modeling, Simulation, Optimization and Numerical Techniques (SMONT 2019) (pp. 64-68). School of Information Management, Jiangxi University of Finance and Economics. [4] Li, X. C., Wang, Q. L., & Lin, G. Q. (2020). Comparative Study on Financial Early Warning Models of Listed Companies Based on Machine Learning Methods. Market Modernization (07), 150-152. doi:10.14013/j.cnki.scxdh.2020.07.070. [5] Zhu, L. Y. (2019). Support Vector Machine for Non-life Insurance Company Bankruptcy Prediction Based on Feature Engineering Application (Master's Thesis, Southwestern University of Finance and Economics). Master's Thesis. https://link-cnki-net-s.webvpn.zjhzcc.edu.cn/doi/10.27412/d.cnki.gxncu.2019.000490 doi:10.27412/d.cnki.gxncu.2019.000490. [6] Zhang, C., Li, M., & Li, Y. (2021). Financial Risk Analysis of Real Estate Bubble Based on Machine Learning and Factor Analysis Model. Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, 40(4), 6493-6504. [7] Ge, H. (2020). Research on the Financial Risk Early Warning of Listed Companies Based on CART Decision Tree Model (Master's Thesis, Shanghai University of Finance and Economics). Master's Thesis. https://link-cnki-net-s.webvpn.zjhzcc.edu.cn/doi/10.27296/d.cnki.gshcu.2020.000851 doi:10.27296/d.cnki.gshcu.2020.000851. [8] Li, S. Y. (2022). Financial Risk Identification Based on Financial Analysis Methods. Economic Research Guide (14), 129-131. [9] Chen, J. (2020). Research on Corporate Financial Early Warning Based on Machine Learning and Text Analysis (Master's Thesis, Shanghai Jiao Tong University). Master's Thesis. https://link-cnki-net-s.webvpn.zjhzcc.edu.cn/doi/10.27307/d.cnki.gsjtu.2020.002723 doi:10.27307/d.cnki.gsjtu.2020.002723. [10] Zhang, C. N., Ren, A. Z., & Lin, Z. D. (2023). Financial Risk Early Warning of Listed Companies—Based on Machine Learning Methods. SME Management and Technology (16), 182-184. [11] Wang, J. M., & Zou, J. W. (2023). Research and Practice on Automated Early Warning System for Commercial Bank Financial Risk. China Financial Computing (11), 77-80. [12] Feng, J. X. (2021). Research on Financial Fraud Identification Model Based on Machine Learning (Master's Thesis, Nanjing University). Master's Thesis. https://link-cnki-net-s.webvpn.zjhzcc.edu.cn/doi/10.27235/d.cnki.gnjiu.2021.000767 doi:10.27235/d.cnki.gnjiu.2021.000767. [13] Zhang, L., Liu, J. P., & Jiang, M. Q. (2021). Application of Integrated Machine Learning Models in Financial Early Warning of Unbalanced Samples. Application of Electronic Technology (08), 34-38. doi:10.16157/j.issn.0258-7998.201234. [14] Jiang, Q. K., & Wang, C. Z. (2023). Research on Financial Risk Early Warning of Internet Enterprises' Overseas Mergers and Acquisitions Based on Stacking Ensemble Learning. Technical Economy (09), 147-160. [15] Chen, J. F., Yu, J., Li, X. Z., & Fan, C. (2023). Financial Investment Risk Early Warning Method for Large Enterprises Based on Machine Learning. Market Outlook (04), 49-51. [16] Powers, D. M. W. (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1), 37-63.