The role of AI in credit risk assessment: Evidence from OECD and BRICS via system GMM and random forest

Doğuş Emin and Ayşegül Aytaç Emin

Finance Research Letters, 2025, vol. 81, issue C

Abstract: This study investigates the impact of artificial intelligence (AI) adoption on credit risk assessment in OECD and BRICS economies by employing both System Generalized Method of Moments (GMM) and Random Forest models. As a first step, a composite AI Adoption Index is constructed to capture the technological maturity of financial institutions with indicators including banking technology spending, the reported frequency of machine learning use in financial institutions based on survey responses, and the extent of digital transformation initiatives. GMM model shows a significant negative relationship between AI adoption and credit risk, while this effect is stronger in BRICS countries. The Random Forest model further validates these findings by capturing non-linear interactions and emphasizing AI's predictive significance through SHAP values.

Keywords: Credit risk; AI adoption index; System generalized method of moments; Random forest (search for similar items in EconPapers)
JEL-codes: C33 G21 G32 O33 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1544612325007585
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:finlet:v:81:y:2025:i:c:s1544612325007585

DOI: 10.1016/j.frl.2025.107499

Access Statistics for this article

Finance Research Letters is currently edited by R. Gençay

More articles in Finance Research Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().