RiskSpan Releases Credit Model 7.1 for NonQM Loans

July 18, 2026
RiskSpan has launched Credit Model 7.1, a NonQM credit model now available within the RiskSpan Platform, designed to analyze loan performance by documentation type using detailed borrower and macroeconomic data.

RiskSpan announced in a press release the release of Credit Model 7.1, a NonQM credit model available within the RiskSpan Platform. The model is built specifically for NonQM collateral and works with the firm’s existing NonQM prepayment model, providing an integrated suite for credit and prepay analysis.

Credit Model 7.1 includes transition state modeling for NonQM assets, segmenting by documentation types such as Bank Statement, DSCR, Full Doc, and Other categories. It uses ten borrower and loan variables, including FICO score, mark to market loan-to-value, debt-to-income ratio, and loan purpose, along with three macroeconomic factors.

The model was trained on about 226,000 NonQM loans totaling $87 billion in unpaid principal balance from January 2018 through August 2025. Additional features include AI powered tape cracking and collateral analysis tools, API access for workflow integration, and a user dashboard for backtesting that is planned for release soon.

The platform delivers a full tape to cash flow workflow for investors and issuers in the NonQM market, which has seen sharply rising issuance volumes since 2020. Credit Model 7.1 is now available to clients using the RiskSpan Platform and Loans Module, with further integrations under development.

We hope you enjoyed this article.

Consider subscribing to one of our newsletters like Finance AI Weekly or Daily AI Brief.

Also, consider following us on social media:

AI in Finance AI Brief AI Brief (X)

More from: Finance

09/10
Grantd Adds Collective Liquidity Tools for Private Share Planning
09/10
62% of Finance Workers Say AI Errors Reached Clients or Decision Makers
09/10
T. Rowe Price Expands Claude Across Investment Teams
09/10
Omega Point Launches Kelly AI Agent for Investment Analysis
09/10
Ant International, Visa and Mastercard Develop Know Your Agent Framework

Subscribe to Finance AI Weekly

Weekly newsletter about AI in finance. Covers AI-driven trading, fintech innovations, and data analytics transforming markets

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You May Also Like