Arlington, VA – July 17, 2026 – RiskSpan, a leading provider of data, modeling and analytics solutions for loan and structured finance investors, today announced the general availability of Credit Model 7.1, a purpose-built NonQM credit model delivered inside the RiskSpan Platform. Paired with RiskSpan’s existing NonQM prepayment model, the launch makes RiskSpan the only vendor offering a purpose-built prepay and credit model suite for NonQM alongside an integrated, tape-to-cashflow workflow in a single environment.

The launch comes as the NonQM market extends a multi-year run of outsized, accelerating growth. Non-QM RMBS issuance nearly doubled year-over-year in the third quarter of 2025 — up 97% to a record $20.9 billion, from $10.6 billion in the same quarter of 2024 — according to Morningstar DBRS. That surge continues a longer trend: Fitch Ratings reports that issuance across its rated Non-QM/Non-Prime RMBS portfolio grew more than 800% between 2020 and 2023, and KBRA projects broader non-agency RMBS issuance, which includes NonQM, to grow another 15% in 2026 to $160 billion. That growth has outrun the tools available to evaluate it: as dealer tapes arrive faster and allocations close on tighter timelines, investors and issuers are increasingly underserved by legacy credit and prepay models built for agency or older non-agency collateral rather than NonQM’s doc-type-driven borrower behavior.

Credit Model 7.1 introduces a full transition-state credit model for NonQM collateral, with each transition estimated independently models for Bank Statement, DSCR, Full Doc, and Other documentation types. The model incorporates ten loan- and borrower-level factors — including FICO, mark-to-market LTV, DTI, and loan purpose — alongside three macroeconomic drivers, and is trained on approximately $87 billion in UPB across roughly 226,000 NonQM loans spanning January 2018 through August 2025. The release also includes AI-powered tape cracking and collateral analysis tools, and API access for clients integrating model output into their own workflows, with a user-facing backtesting dashboard coming soon. 

Divas Sanwal, Head of Modeling at RiskSpan, added: “NonQM borrower behavior varies meaningfully by documentation type, and generic credit and prepay frameworks simply don’t capture that. Credit Model 7.1 was built from the ground up on NonQM collateral, segmented by doc type, and validated with published backtesting — giving risk teams, auditors, and counterparties the transparency they need to stand behind the model.” 

The NonQM analytics market today is served by third-party models fit on broader non-agency collateral, standalone cashflow engines, and in-house models built on limited internal history. RiskSpan is the only vendor combining purpose-fit NonQM prepay and credit models, loan-level workflow tools, and proprietary historical data in one platform. Credit Model 7.1 is available now to RiskSpan Platform and Loans Module clients, with container deployment and additional integrations planned in later phases. 

About RiskSpan 

RiskSpan delivers a single analytics solution for loan and structured finance (public and private) credit investors of any size – to make faster, more precise trading and portfolio management decisions and meet reporting requirements without manual work, multiple vendors and internal solutions. 

RiskSpan’s contributions span the full lifecycle of structured finance pricing and data operations, including advanced cash flow and valuation models, automated data pipelines, quality controls, and reconciliation frameworks designed to meet the demands of institutional investors, dealers, and risk managers. 

Learn more at www.riskspan.com. 

For media inquiries, please contact: 

Samantha Wilcox 
sawilcox@riskspan.com 
425-652-6700