Enhancing SME Credit Risk Prediction with Soft Information: Evidence from Machine Learning Models
Main Article Content
Keywords
SME credit risk, soft information, machine learning, random forest
Abstract
This study examines whether integrating soft information with machine learning models can improve credit risk prediction for small and medium-sized enterprises (SMEs). Both financial (hard) and non-financial (soft) variables are incorporated into the analysis by using firm-level data from A-share listed companies. The study compares the performance of logistic regression, random forest, and XGBoost models under different data frameworks. The results show that soft information significantly enhances model performance when combined with hard information and nonlinear models. Feature importance analysis further indicates that although financial variables remain the primary predictors, soft information plays a meaningful role in credit risk prediction. Overall, the findings suggest that integrating soft information with machine learning provides a more comprehensive and effective approach to SME credit risk assessment. This study highlights the value of soft information and emphasizes the importance of combining data diversity with advanced modeling techniques.
References
- [1]Mhlanga, D. (2021b). Financial Inclusion in Emerging Economies: The application of machine learning and artificial intelligence in credit risk assessment. International Journal of Financial Studies, 9(3), 39. https://doi.org/10.3390/ijfs9030039
- [2]Djeundje, V. B., Crook, J., Calabrese, R., & Hamid, M. (2020). Enhancing credit scoring with alternative data. Expert Systems With Applications, 163, 113766. https://doi.org/10.1016/j.eswa.2020.113766
- [3]Bussmann, N., Giudici, P., Marinelli, D., & Papenbrock, J. (2020c). Explainable machine learning in credit risk management. Computational Economics, 57(1), 203–216. https://doi.org/10.1007/s10614-020-10042-0
- [4]Altman, E. I. (1968). FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND THE PREDICTION OF CORPORATE BANKRUPTCY. The Journal of Finance, 23(4), 589–609. https://doi.org/10.1111/j.1540-6261.1968.tb00843.x
- [5]Ohlson, J. A. (1980). Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research, 18(1), 109. https://doi.org/10.2307/2490395
- [6]Stiglitz, J. E., & Weiss, A. (1981). Credit Rationing in Markets with Imperfect Information. The American Economic Review, 71(3), 393–410. http://www.jstor.org/stable/1802787
- [7]Liberti, J. M., & Petersen, M. A. (2018b). Information: hard and soft. The Review of Corporate Finance Studies, 8(1), 1–41. https://doi.org/10.1093/rcfs/cfy009
- [8]Grunert, J., Norden, L., & Weber, M. (2004). The role of non-financial factors in internal credit ratings. Journal of Banking & Finance, 29(2), 509–531. https://doi.org/10.1016/j.jbankfin.2004.05.017
- [9]Vapnik, V. N. (2013). The nature of statistical learning theory. Springer Science & Business Media.
- [10]Lessmann, S., Baesens, B., Seow, H., & Thomas, L. C. (2015). Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research. European Journal of Operational Research, 247(1), 124–136. https://doi.org/10.1016/j.ejor.2015.05.030
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.