ArticleOpen Access http://dx.doi.org/10.26855/acc.2026.09.005
Research on the Stability and Extreme Scenario Response of Credit Parameter Forecasting Models Integrating Survival Analysis and Machine Learning
Cewen Chi
Quant Analytics, VWH Capital, Dallas, TX 75201, USA.
*Corresponding author: Cewen Chi
Published: July 23, 2026
Abstract
Credit parameter prediction is often influenced by factors such as sample truncation, variations in default timing, nonlinear characteristic coupling, and tail shock disturbances. A single modeling framework frequently fails to simultaneously address time-keeping ability, prediction accuracy, and result stability. To overcome this challenge, this study integrates the strengths of survival analysis—effective in identifying default durations and changes in risk rates—with the fitting capabilities of machine learning, which excels at handling high-dimensional features and complex relationships, to develop a robust credit parameter prediction model. The model's stability and response characteristics are evaluated across three dimensions: sample perturbation, time rolling, and extreme scenario shocks. Results indicate that the fused modeling approach enhances resilience in risk time series identification, tail sample adaptation, and mitigation of abnormal fluctuations. Additionally, it improves correction capabilities for parameter shifts and response delays under extreme conditions. This methodology enhances the continuity, interpretability, and scenario adaptability of credit risk measurement outcomes.
Keyword
Survival analysis; machine learning; credit parameter prediction; model stability
References
[1] Giovanni MS, Azahel GSP, Idalia MLDF. Credit portfolio assessment using machine learning: a case study of a Mexican non-bank financial institution. Procedia Comput Sci. 2026;277:841-849.
[2] Anastasiou D, Ballis A, Kallandranis C, et al. Positive COVID-19 related sentiment, economic uncertainty & risk management implications. J Bank Regul. 2025;27(1):2-2.
[3] Yetiz F, Ciğer A, Kayakuş M, et al. Prediction of financial soundness index for viability in the European banking system using machine learning. SAGE Open. 2025;15(3).
[4] Heß LV, Damásio B. Machine learning in banking risk management: mapping a decade of evolution. Int J Inf Manag Data Insights. 2025;5(1):100324-100324.
[5] Seitshiro BM, Govender S. Credit risk prediction with and without weights of evidence using quantitative learning models. Cogent Econ Finance. 2024;12(1).
[6] Haque AMF, Hassan MM. Bank loan prediction using machine learning techniques. Am J Ind Bus Manag. 2024;14(12):1690-1711.
[7] Zhao Y. Research on financial credit risk of manufacturing enterprises under heterogeneous data based on machine learning. Acad J Bus Manag. 2024;6(11).
[8] Liu T, Ma Y, Yang J, et al. Comparative temporal analysis of SVM-based machine learning techniques for bank risk assessment. In: Proceedings of the 2nd International Conference on Financial Technology and Business Analysis (part3). Danubius University of Galaţi; 2023:625-650.
[9] Yuan F. Bank green credit risk assessment and management by mobile computing and machine learning neural network under the efficient wireless communication. Wirel Commun Mob Comput. 2022;2022.
Copyright
© 2026 by the author(s).
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND) license, which permits non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited and is not modified or adapted.
https://creativecommons.org/licenses/by-nc-nd/4.0/
How to cite this paper
Research on the Stability and Extreme Scenario Response of Credit Parameter Forecasting Models Integrating Survival Analysis and Machine Learning
How to cite this paper: Cewen Chi. (2026) Research on the Stability and Extreme Scenario Response of Credit Parameter Forecasting Models Integrating Survival Analysis and Machine Learning. Advances in Computer and Communication, 7(3), 139-143.
DOI: http://dx.doi.org/10.26855/acc.2026.09.005