Author(s)

MingYue Gao

Affiliation(s)

School of Mathematics and Statistics, Guangxi Normal University, Guilin 541006, Guangxi, China.

Corresponding Author

MingYue Gao

ABSTRACT

In the era of big data, the financial industry is facing new challenges and opportunities. Through big data and artificial intelligence technology, we can more accurately assess and manage various types of financial risks, including credit risk, market risk, fraud risk, etc. In this paper, the decision tree model is used to model and analyze the credit risk in financial risk, and the financial risk prevention and control system is established. For credit risk, according to the bank customer information data, after data processing, the decision tree classification method is used to judge whether the customer may default in the future through the customer's basic information, and finally the main discriminant basis is age, expected income, balance and number of credit cards. Then, from the five dimensions of establishing a sound risk assessment and early warning mechanism, improving citizens' financial risk awareness, promoting the construction of financial stability guarantee fund, strengthening industry supervision and self-discipline, and improving the legal and regulatory system, feasible suggestions are put forward for financial risks.

KEYWORDS

Financial credit risk; Machine learning; Data mining; Decision tree model

CITE THIS PAPER

MingYue Gao. Financial credit risk assessment based on machine learning. Trends in Social Sciences and Humanities Research. 2024, 2(4): 38-43. DOI: 10.61784/tsshr3009.

REFERENCES

[1] Fisher R A. The use of multiple measurements in taxonomic problems. Annals of eugenics, 1936, 7(2): 179-188.

[2] Wiginton J C. A note on the comparison of logit and discriminant models of consumer credit behavior. Journal of Financial and Quantitative Analysis, 1980, 15(3): 757-770.

[3] Makowski P. Credit scoring branches out. Credit World, 1985, 75(1): 30-37.

[4] Coats P K, Fant L F. Recognizing financial distress patterns using a neural network tool. Financial management, 1993: 142-155.

[5] Obare D, Murary M. Comparison of Accuracy of Support Vector Machine Model and Logistic Regression Model in Predicting Individual Loan Defaults. Am. J. Appl. Math. Stat, 2018, 6(6): 266-271.

[6] Chopra A, Bhilare P. Application of ensemble models in credit scoring models. Business Perspectives and Research, 2018, 6(2): 129-141.

[7] Ampountolas A, Nyarko Nde T, Date P, et al. A machine learning approach for micro-credit scoring. Risks, 2021, 9(3): 50.