ARTIFICIAL INTELLIGENCE-DRIVEN CREDIT SCORING MODELS AND THEIR IMPLICATIONS FOR FINANCIAL REPORTING TRANSPARENCY IN NIGERIAN DEPOSIT MONEY BANKS
Keywords:
Artificial Intelligence, Credit Scoring, Financial Reporting Transparency, Nigerian Banks, Investor Confidence, Advanced AnalyticsAbstract
This study examines the disclosure of artificial intelligence (AI)–driven credit scoring models among Nigerian deposit money banks and evaluates their implications for financial reporting transparency. It will also investigate the scope and quality of disclosure, the forces that shape disclosure in practice, and the effects of disclosure on the confidence of stakeholders in the correctness and validity of the financial statements.The research methodology for this study is qualitative with a focus on using secondary sources like reports, statements, reporting requirements for governance practices both by the Central Bank of Nigeria and Securities Exchange Commission for compliance reporting requirements and necessary studies. The study will use a technique for analyzing themes in determining the disclosure practices in using technology like AI for credit scoring practices with a focus on governance practices and requirements for transparency, risks disclosure requirements for impairment reporting under the guidelines outlined in IFRS-9. The findings indicate that the level of disclosure on the use of AI in credit scoring is higher (59%) in Tier-1 and global banks compared to Tier-2 and local banks (34%). Key elements that contribute to better disclosure practices include the use of AI and advanced analytics in credit risk management (68%), governance and oversight of credit models (61%), effect on impairment and loan loss provisioning (55%), and explainability (38%). Factors hindering disclosure practices include the complexity of AI models (66%), lack of regulatory guidelines (58%), concerns regarding sensitive information (54%), and limitations in technical reporting capabilities (49%). Perceptions on stakeholder involvement reveal that effective disclosure practices enhance credibility in disclosed credit risk amounts (41%), credibility in financial reporting (38%), and overall transparency (39%).Conclusion: There is a need for transparency and thorough disclosure of practices involved in AI-powered credit scoring in order to improve the credibility of financial reports, and ultimately boost investor confidence in Nigerian deposit money banks.References
Ajibade, A. T., Akintoye, I. R., & Ajah, C. C. (2025). Artificial Intelligence on Risk Management Engineering in Non-financial Service Companies Listed in Nigeria. International Journal of Economics, Business and Management Research, 9(05), 479-503. https://www.ijebmr.com/uploads/pdf/archivepdf/2025/IJEBMR_1628.pdf
Basel Committee on Banking Supervision (2021) – Model Risk Management
https://www.bis.org/bcbs/publ/d516.pdf
Caldarola, B., Mazzilli, D., Napolitano, L., Patelli, A., & Sbardella, A. (2024). Economic complexity and the sustainability transition: A review of data, methods, and literature. Journal of Physics: Complexity, 5(2), 022001. https://iopscience.iop.org/article/10.1088/2632-072X/ad4f3d/meta
Central Bank of Nigeria (2023) – Financial Stability Report
https://www.cbn.gov.ng/documents/fsr.asp
Faheem, M. A. (2021). AI-driven risk assessment models: Revolutionizing credit scoring and default prediction. Iconic Research And Engineering Journals, 5(3), 177-186. https://www.researchgate.net/profile/Muhammad-Ashraf-Faheem/publication/385074551_AI-Driven_Risk_Assessment_Models_Revolutionizing_Credit_Scoring_and_Default_Prediction/links/6713e02e035917754c09413e/AI-Driven-Risk-Assessment-Models-Revolutionizing-Credit-Scoring-and-Default-Prediction.pdf
IASB (2023) – IFRS 9 Financial Instruments
Jakubik, P., & Kadioglu, E. (2022). Factors affecting bank loan quality: a panel analysis of emerging markets. International Economics and Economic Policy, 19(3), 437-458. https://link.springer.com/article/10.1007/s10368-021-00520-7
Mesioye, O., & Bakare, I. A. (2024). Evaluating financial reporting quality: Metrics, challenges, and impact on decision-making. Int J Res Public Rev, 5(10), 1144-1156.
OECD (2021) – AI, Machine Learning and Financial Services
https://www.oecd.org/finance/artificial-intelligence-machine-learning-financial-services.htm.
Samuel-Ogbu, I. (2022). Digital technology and the transformation of the Nigerian banking system: The operators’ perspective. Economic and Financial Review, 60(4), 133-150. https://dc.cbn.gov.ng/efr/vol60/iss4/11/
Okoliko, E. O., Ayetigbo, A. O., Ifegwu, I. J., & Chidiebere, N. U. (2023). Artificial Intelligence Impact in Revolutionizing the Nigerian Banking Industry: An Assessment of Selected Deposit Money Banks in Abuja. Funksec here, 5(2), 120-131. https://achieverssciencejournal.org/ajosrojs/index.php/ajosr/article/view/153
Yadava, A. (2023). AI-Driven Credit Risk Assessment: Enhancing Financial Decision-Making in SME Lending Using Deep Learning Algorithms. International Journal of Innovative Research in Computer and Communication Engineering, 11(13), 10-15680. https://www.researchgate.net/
Downloads
Published
Issue
Section
License
Copyright (c) 2026 JOURNAL OF BEHAVIOURAL ACCOUNTING

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.