Beyond scores underwriting: An explainable, inclusive and fraud-resilient underwriting framework leveraging banking relationship and transactional data

Abstract

Traditional credit underwriting models rely heavily on bureau-based scores, limiting access to credit for thin-file and credit-invisible consumers. This paper focuses on a large and growing segment described as ‘Emerging Achievers’, including young adults, migrants and gig workers who demonstrate responsible financial behaviour through banking activity but remain underserved by conventional models. It argues for a shift from score-led approaches to a relationship-based underwriting framework that incorporates banking relationships and transactional data alongside traditional measures. The paper explains how open banking and emerging open finance ecosystems enable the use of permissioned financial data, including income patterns, spending behaviour and nontraditional payment histories, to provide a more complete and explainable view of consumer risk. It outlines a framework that integrates relationship-based segmentation, transactional underwriting and embedded fraud detection, supporting more accurate, transparent and inclusive credit decisions while maintaining regulatory alignment. Case evidence indicates improved decisioning performance and expanded access without compromising risk appetite. The paper concludes that adopting a relationship-driven, data-led approach offers lenders a scalable pathway to serve underserved segments while balancing inclusion, explainability and fraud resilience. It also highlights implementation considerations — including data governance, model transparency, customer consent and operational integration — as essential enablers of sustainable deployment at scale. This article is also included in The Business & Management Collection which can be accessed at https://hstalks.com/business/.