Research on the Implementation Path and Effectiveness Evaluation of Explainable Artificial Intelligence in China's Financial Regulation

DOI: https://doi.org/10.62517/jse.202511509

Author(s)

Wenjing Zhang

Affiliation(s)

School of Economics, Guangzhou College of Commerce, Guangzhou, Guangdong, China

Abstract

This study aims to systematically analyze the implementation path and effectiveness evaluation system of Explainable Artificial Intelligence (XAI) technology in China's financial supervision field. By integrating methods such as case studies, and the construction of a multi-dimensional evaluation framework, the study sorts out the regulatory evolution, technical architecture, and typical application scenarios of XAI in China's financial supervision in recent years. The research finds that by enhancing the transparency and traceability of AI decisions, XAI can effectively alleviate the "black box" dilemma in supervision. For instance, it increases the identification accuracy rate to 83% in anti-money laundering (AML) monitoring and reduces the time for credit supervision review by 60%. However, the current application still faces challenges such as insufficient technical adaptability, fragmented standards, and a shortage of interdisciplinary talents. This study proposes a four-level technical architecture centered on the core concept of "explainable - verifiable - intervenable" and constructs a multi-dimensional evaluation indicator system covering technical effectiveness, supervision efficiency, risk prevention and control, and compliance. The conclusions indicate that the implementation of XAI needs to be promoted in a coordinated manner through a three-dimensional path of technological tool innovation, institutional collaboration, and talent cultivation, so as to support the transparent, precise, and intelligent transformation of China's financial supervision system in the digital era.

Keywords

Explainable Artificial Intelligence (XAI); Financial Supervision; Implementation Path; Effectiveness Evaluation; Regulatory Technology (RegTech)

References

[1] Mill E R, Garn W, Ryman-Tubb N F, et al. Opportunities in real time fraud detection: an explainable artificial intelligence (XAI) research agenda. International Journal of Advanced Computer Science and Applications, 2023, 14(5): 1172-1186. [2] Anang A N, Ajewumi O E, Sonubi T, et al. Explainable AI in financial technologies: Balancing innovation with regulatory compliance. International Journal of Science and Research Archive, 2024, 13(1): 1793-1806. [3] Roberts H, Cowls J, Morley J, et al. The Chinese approach to artificial intelligence: an analysis of policy, ethics, and regulation[M]. Ethics, governance, and policies in artificial intelligence, 2021: 47-79. [4] Bura C, Jonnalagadda A K, Naayini P. The role of explainable ai (xai) in trust and adoption. Journal of Artificial Intelligence General science, 2024, 7(01): 262-277. [5] Liu Y, Peng J, Shen X D, et al. Research on the Impact of AI Technology Application on Financial Industry: Taking ChatGPT as an Example. Contemporary Financial Research, 2023, 6(11): 37-53. [6] Tang J C, Liu L. Research on the Application of "AI + Insurance" Model in the Era of Insurance Technology. Southwest Finance, 2019, (05): 63-71. [7] Lan H, Xiong X P, Hu Yingjie. Research on the Development Problems and Innovative Supervision of Internet Finance under the Background of Big Data. Southwest Finance, 2019, (03): 80-89. [8] Yeo W J, Van Der Heever W, Mao R, et al. A comprehensive review on financial explainable AI. Artificial Intelligence Review, 2025, 58(6): 1-49. [9] Filipova I A. Legal regulation of artificial intelligence: Experience of China. Journal of Digital Technologies and Law, 2024, 2(1): 46-73. [10]Amirineni S. Enhancing Predictive Analytics in Business Intelligence through Explainable AI: A Case Study in Financial Products. Journal of Artificial Intelligence General science, 2024, 6(1): 258-288. [11]Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., et al. Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI. Information Fusion, 2020, (58): 82-115. [12]Zhang L, Liang X, Yang W, et al. Identification of the formation temperature field by explainable artificial intelligence: A case study of Songyuan City, China. Energy, 2025, 319. [13]Aljunaid S K, Almheiri S J, Dawood H, et al. Secure and Transparent Banking: Explainable AI-Driven Federated Learning Model for Financial Fraud Detection. Journal of Risk & Financial Management, 2025, 18(4). [14]Katterbauer K. Financial regulation reforms in China–can artificial intelligence be a gamechanger to more sustainable financial regulations. Financial Law Review, 2024, 36(4): 1-33. [15]Ahmadi S. Advancing fraud detection in banking: Real-time applications of explainable ai (xai). Journal of Electrical Systems, 2022, 18(4): 141-150.