Artificial Intelligence in Banking Risk Management: A Bibliometric Analysis

Laura Aibolovna Kuanova, A. N. Otegen

2026

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.3390/ijfs14040093
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Artificial intelligence (AI) is increasingly embedded in banking risk management, yet academic research on this topic remains conceptually fragmented and dispersed across multiple disciplines. This study examines global publication trends and thematic structures related to AI applications in banking risk management through a bibliometric analysis of 83 peer-reviewed articles indexed in the Web of Science Core Collection for the period 2020–2024. The analysis was conducted using Bibliometrix (R-package, version 4.1), its web interface Biblioshiny (2024 release), to evaluate publication dynamics, citation performance, authorship patterns, and thematic clusters. Results show a substantial rise in scientific interest, with annual publication growth of 41.4% and international co-authorship reaching 30%. Five major thematic clusters were identified, including AI-enabled credit risk assessment, fraud detection, operational and cyber-risk mitigation, FinTech adoption, and regulatory compliance. Approximately 30% of the articles appeared in the top ten journals publishing on the topic, and the dataset recorded more than 3800 cited references. The findings indicate that AI contributes to enhanced predictive accuracy, real-time anomaly detection, and supervisory efficiency in banking risk management, while persistent challenges relate to model transparency, data quality, and regulatory adaptation. This study offers a systematic, data-driven understanding of the intellectual landscape and research evolution of AI-driven banking risk management from 2020 to 2024.