University of Plymouth.
Research Article
World Journal of Advanced Research and Reviews, 2023, 17(03), 1095-1106
Received on 27 January 2023; revised on 07 March 2023; accepted on 10 March 2023
The field of credit scoring sees a transformation through machine learning, which yields better prediction results when credit is opened to new populations. Traditional credit scoring systems, which base their predictions on limited financial records, fail to serve millions of unbanked and underbanked people with access to credit. Overlooked data from transaction histories combined with mobile payment records and online behavioral analysis enables ML-based credit assessments to boost lender decision-making precision through improved risk assessment. The research investigates how ML affects credit scoring operations by studying different prediction models that best determine creditworthiness. An evaluation of typical lending practices and ML-based methods demonstrates how automated fair and rapid loan processing emerges as their key benefits. This study utilizes data analytics examinations combined with banking and fintech industry case investigations as research methods. The findings demonstrate better access to credit and reduced bias and risk of default possible through ML implementation. Regular financial institutions and policymakers can use this research to understand how they should utilize Machine Learning techniques to improve lending accessibility while preserving integrity.
Machine Learning; Credit Scoring; Risk Analysis; Fraud Detection; Financial Inclusion; Data Analytics
Preview Article PDF
GBEMINIYI DEBORAH ONIPEDE. The role of machine learning in enhancing credit scoring models for financial inclusion. World Journal of Advanced Research and Reviews, 2023, 17(3), 1095-1106. Article DOI: https://doi.org/10.30574/wjarr.2023.17.3.0400