Author(s)

Yun Li^*, RongHua Li

Affiliation(s)

School of Finance and Economics, Hainan Vocational University of Science and Technology, Haikou 571126, Hainan, China.

Corresponding Author

Yun Li

ABSTRACT

Machine learning (ML) technology is profoundly reshaping digital financial services and risk management systems. This paper systematically reviews the current applications of ML in four core scenarios: credit scoring, fraud detection, algorithmic trading, and customer segmentation. Literature analysis reveals that deep learning and ensemble methods demonstrate superior performance compared to traditional statistical approaches in financial risk prediction tasks, with supervised learning techniques predominating in fraud detection systems and algorithmic trading becoming increasingly prevalent in capital markets. However, the trade-off between model interpretability and predictive performance remains a critical challenge in regulated financial environments. Furthermore, data quality limitations and regulatory compliance requirements impose substantial constraints on model deployment. This review identifies key research gaps and suggests that future developments must prioritize explainable AI techniques, privacy-preserving methods, and regulatory-compliant frameworks to enable the sustainable adoption of ML in the financial sector.

KEYWORDS

Machine learning; Digital finance; Credit scoring; Fraud detection; Model interpretability

CITE THIS PAPER

Yun Li, RongHua Li. Machine learning in digital finance: applications, methods and challenges. World Journal of Economics and Business Research. 2025, 3(4): 22-27. DOI: https://doi.org/10.61784/wjebr3063.

REFERENCES

[1] Vukovis DB, Dekpo-Adza S, Matovic S. AI integration in financial services: a systematic review of trends and regulatory challenges. Humanit Soc Sci Commun, 2025, 12(1): 1-29.

[2] Salehpour Arash, Samadzamini Karim. Machine Learning Applications in Algorithmic Trading: A Comprehensive Systematic Review. International Journal of Education and Management Engineering (IJEME), 2023, 13(6): 41.

[3] Congress.gov. Artificial Intelligence and Machine Learning in Financial Services. 2025, 03. https://www.congress.gov/crs-product/R47997.

[4] International Association of Insurance. Regulation and supervision of artificial intelligence and machine learning (AI/ML) in insurance: a thematic review. 2023, 12. https://www.iais.org/uploads/2023/12/Regulation-and-supervision-of-AI-ML-a-thematic-review.pdf.

[5] Nazareth Noella, Reddy Yeruva Venkata Ramana. Financial applications of machine learning: A literature review. Expert Systems with Applications, 2023, 219: 119640.

[6] Svitla Team. Machine Learning for Credit Scoring: Benefits, Models, and Implementation Challenges. 2024. https://svitla.com/blog/machine-learning-for-credit-scoring.

[7] Shi S, Tse R, Luo W, et al. Machine learning-driven credit risk: a systemic review. Neural Computing and Applications, 2022, 34(17): 14327-14339.

[8] Hashimoto Ryuichiro, Miura Kakeru, Yoshizaki Yasunori. Application of Machine Learning to a Credit Rating Classification Model: Techniques for Improving the Explainability of Machine Learning. Bank of Japan, 2023: 23-E-6.

[9] Wahyono Teguh, David Felix. A Systematic Review of Machine Learning-Based Approaches for Financial Fraud Detection. Journal of System and Management Sciences, 2025, 15(1): 69-84.

[10] Infosys BPM. Revolutionising fraud detection in banking: The impact of AI and machine learning. 2025. https://www.infosysbpm.com/blogs/financial-services/ai-fraud-detection-and-impact-of-ai-and-machine-learning.html.

[11] Kumar Dhiraj. Implementing Customer Segmentation Using Machine Learning [Beginners Guide]. 2025. https://neptune.ai/blog/customer-segmentation-using-machine-learning.

[12] Munira Mosa Sumaiya Khatun. Digital transformation in banking: A systematic review of trends, technologies, and challenges. Technologies, and Challenges, 2025.