Author(s): Braja Kishore Mishra, Subash Ch. Nath, Sunil K. Dhal, Rajat Kumar Baliarsingh
Traditional credit-risk assessment systems—anchored in financial histories, repayment records, and collateral adequacy—often fail to capture the human behaviour behind creditworthiness. Millions of individuals in emerging economies remain outside the formal credit ecosystem because they lack standard financial footprints despite demonstrating social reliability and economic potential. This study introduces an innovative model called the Enhanced Social Score Metric Index (E-SSMI) that fuses behavioural, digital, relational, and ethical indicators into conventional risk analytics. Using simulated validation across representative borrower cohorts, the paper demonstrates how integrating social scoring metrics substantially improves predictive accuracy and inclusivity. The research also situates the E-SSMI within the global dialogue on responsible finance, data ethics, and sustainable credit inclusion. Findings suggest that financial institutions adopting socially aware algorithms can reduce default probabilities while expanding their lending portfolios toward unbanked and under-banked populations. The paper concludes by proposing governance safeguards, ethical-AI protocols, and a policy roadmap for regulators and lenders.