<![CDATA[his study aims to explore the role of seller metrics on e-commerce platforms in assessing microcredit risk through a Systematic Literature Review (SLR) approach. The study reviewed recent literature from 2020 to 2025 from academic databases such as Scopus, DOAJ, and Google Scholar, using keywords like "seller metrics," "microcredit risk," "credit scoring," and "machine learning." Findings indicate that seller metrics, including long-term payment behavior, transaction frequency, purchase consistency, and seller engagement on digital platforms, significantly enhance the accuracy, stability, and fairness of credit scoring models compared to traditional financial indicators. The integration of alternative data and the application of machine learning models, particularly boosting algorithms, further strengthen predictive capabilities for credit risk. Nonetheless, challenges related to formal validation, algorithmic bias, and model interpretability remain critical. Future research is recommended to develop a comprehensive predictive framework and bias mitigation strategies to support inclusion and fairness in microcredit risk assessment.]]>
Copyrights © 2026
