Data Management Archives

AI Isn’t Coming to Structured Finance. It’s Already Here.

At SFVegas 2026, RiskSpan had a front-row seat to one of the most consequential conversations happening in our industry right now. I moderated a session on Agentic AI and the Securitization Lifecycle, while our CEO, Bernadette Kogler, participated in a panel on AI applications in structured finance. Across both rooms, the message was the same: we are done experimenting. We are redesigning workflows.

The distinction that framed everything was simple but important. Copilots assist. Agents orchestrate. We are moving from AI that enhances what humans do to AI that executes complex, multi-step workflows — with humans supervising the process rather than driving every step. That shift changes everything about how we think about structured finance operations.

And structured finance, it turns out, is almost perfectly suited for this moment. It is document-heavy, multi-party, process-driven, and data-intensive. From origination through surveillance, the lifecycle is fundamentally workflow-based. Panelists across both sessions shared real examples already in production: legal document review compressed from days to hours, AI-powered loan tape scrubbing before cash flow calculations, prompt-driven scenario generation replacing manual model configuration, and surveillance scaled across hundreds of deals per month. One striking observation: the future interface for structured finance may not be a UI at all — it may be entirely driven by prompts.

But the panels were equally clear-eyed about what has to come first. Sixty-five percent of financial services firms are actively using AI, yet only 13% have deployed it across production processes. The gap between those two numbers is largely a data problem. The most sophisticated AI cannot overcome poor inputs, inconsistent loan tapes, or legacy system constraints. Firms that want to lead need to fix the foundation before layering on orchestration.

Explainability matters just as much. With the EU AI Act and US fair lending enforcement raising the stakes, auditable, transparent models are not optional. And governance is shifting from “human in the loop” to “human over the loop” — a subtle but meaningful difference that requires defined accountability, model drift monitoring, and clear operational guardrails.

The one-year outlook from both panels was notably concrete. Expect AI agents managing defined surveillance workflows, deeper cross-platform integration, and a sharper divide between early movers and everyone else. The competitive advantage will go to firms that clean their data, build explainability into their models from day one, and embed AI into operations — not just into pilot programs.

Structured finance has always rewarded process discipline and deep domain expertise. That doesn’t change in an agentic world — if anything, it becomes more critical. The quality of an AI agent’s output is only as good as the prompts and parameters guiding it, and designing those well requires people who understand cash flow waterfalls, covenant structures, and credit risk at a fundamental level. Agentic AI doesn’t replace that expertise. It amplifies it. The firms that understand that will define the next chapter.

At RiskSpan, we have spent years building at exactly this intersection — combining deep structured finance domain knowledge with purpose-built analytics infrastructure. That foundation is what makes it possible to deploy AI that actually works in production, not just in demos. The opportunity in front of our clients right now is significant, and we are focused on helping them capture it.

The Data Model That Powers Private ABF: Why Purpose-Built Architecture Changes Everything

Private asset-backed securities don’t follow the same rules as public securitizations. The structures are more diverse. The triggers are more nuanced. The collateral is more diverse. And yet, most market participants still try to manage these instruments with tools designed for a different world entirely—or worse, with disconnected spreadsheets that multiply risk with every manual handoff.

RiskSpan’s Private ABF platform was built specifically to solve this problem. Not as an adaptation of existing tools, but as a purpose-built data architecture designed from the ground up for the unique demands of private structured finance. The difference isn’t incremental—it’s foundational.

Built for the Full Lifecycle

RiskSpan’s Private ABF platform isn’t just a database—it’s a relational architecture where every entity maintains its identity and relationships across the entire deal lifecycle. The platform connects deals to their tranches, tranches to their collateral, collateral to individual loans, and all of these to the triggers, waterfalls, fees, and reserves that govern cash flow distribution.

This matters because private ABS transactions aren’t static. Collateral performs. Triggers trip. Waterfalls redirect. Reserves build and release. A platform that can’t maintain these relationships in real time isn’t managing deals—it’s creating snapshots that are stale before they’re finished.

Loan-Level Depth That Powers Real Analysis

At the heart of any ABS transaction is the underlying collateral. RiskSpan’s Private ABF platform maintains comprehensive loan-level data with over 200 attributes per asset, tracking everything from origination characteristics through current performance status. This includes credit metrics like FICO scores and debt-to-income ratios, property and collateral details, payment history and delinquency tracking, modification and loss mitigation status, and ARM reset schedules and rate mechanics.

The platform currently manages nearly half a billion loan records across active transactions. Each loan maintains its full history—not just current state, but the complete trajectory that informs forward-looking projections. When you run a cash flow model, you’re not working from aggregated pool statistics. You’re working from the actual loans, with their actual characteristics, generating projections that reflect real collateral behavior.

Depth for Esoteric Structures

RiskSpan’s Private ABF platform currently supports over several collateral types and structures. Each asset class has its own performance characteristics, prepayment behaviors, and loss dynamics. The platform’s architecture accommodates this diversity without forcing artificial standardization.

But diversity in collateral is only part of the challenge. Private ABS triggers represent some of the most complex conditional logic in structured finance. Unlike standardized agency delinquency tests, private deal triggers can involve multi-step calculations with lookback periods, cure provisions that allow temporary breaches, step-rate adjustments that phase in over time, and early amortization events with distinct severity levels.

The platform models triggers as executable logic, not static documentation. When a trigger breaches, the system knows what happens next—which waterfall priorities shift, which reserve requirements change, which reporting obligations activate. This is the deal’s immune system, and it needs to function in real time.

Time-Series Without the Chaos

Every entity in RiskSpan’s Private ABF platform exists in time. The platform maintains separate performance histories for tranches, collateral pools, fees, and reserves—each keyed by reporting date to enable point-in-time reconstruction of any deal state.

This architecture solves one of the most persistent problems in private ABF operations: answering the question “what did we know, and when did we know it?” Whether for regulatory compliance, investor reporting, or internal risk management, the ability to reconstruct historical deal states isn’t a luxury—it’s a requirement that spreadsheet-based approaches simply cannot meet reliably.

The Waterfall as Working Code

Cash flow waterfalls in private ABF can run to dozens of steps with conditional branches, pro-rata splits, and priority reversions. RiskSpan’s Private ABF platform models these waterfalls as executable payment sequences—not flowcharts, but actual logic that routes cash from sources to destinations based on current deal state.

Each waterfall step defines its priority in the payment sequence, its source of funds and destination, its allocation basis (pro-rata, sequential, or targeted), and the conditions under which it activates or suspends.

When combined with the platform’s cash flow engine, these waterfall definitions become working models. You can project payments under any scenario, stress collateral performance, and see exactly how cash moves through the structure period by period.

An Architecture Built for AI

The same architectural principles that make RiskSpan’s Private ABF platform effective for traditional analytics make it exceptionally well-suited for artificial intelligence and machine learning applications. This isn’t a coincidence—it’s a consequence of building a data model that prioritizes structure, relationships, and semantic clarity.

AI systems thrive on clean, well-organized data with explicit relationships. RiskSpan’s Private ABF platform delivers exactly this: normalized entities with consistent identifiers, clear hierarchies from deals down to individual loans, and temporal versioning that distinguishes current state from historical snapshots. When an AI model needs to understand a transaction, it doesn’t have to infer structure from unstructured sources—the relationships are already defined and traversable.

The platform’s semantic richness enables natural language interfaces that actually work. Because every field has meaning within a consistent schema, AI can translate questions like “show me deals where the senior OC trigger is within 50 basis points of breach” into precise queries without ambiguity. The loan-level depth means AI models can identify patterns across hundreds of millions of records—finding correlations between origination characteristics and performance outcomes that would be invisible to traditional analysis.

Time-series architecture is particularly critical for AI applications. Machine learning models for credit risk, prepayment prediction, and loss forecasting require historical sequences, not point-in-time snapshots. RiskSpan’s Private ABF platform maintains this temporal context natively, enabling training datasets that capture how loans and deals evolve over their lifecycles.

RiskSpan is already deploying AI capabilities on this foundation: automated anomaly detection that flags unusual performance patterns, intelligent document extraction that populates deal records from offering documents, natural language querying that makes complex analytics accessible to non-technical users, and predictive models that leverage the full depth of loan-level history. The platform doesn’t just store data—it organizes knowledge in a form that AI can reason about.

Designed for the Enterprise

RiskSpan’s Private ABF platform operates as a multi-tenant platform with granular access controls. Every record carries client and user identifiers that enable sophisticated permission model—issuers see their deals, investors see their positions, servicers see their portfolios, and rating agencies see what they’re authorized to review.

This isn’t just about security (though it is that). It’s about enabling collaboration across the structured finance ecosystem without compromising confidentiality. A single platform can serve all participants in a transaction, each with their appropriate view of the data.

Built for What Comes Next

Private ABS is an evolving market. New asset classes emerge. New structures get tested. New regulatory requirements arrive. RiskSpan’s Private ABF platform accommodates this evolution through flexible schema design that allows custom attributes without requiring database modifications.

When a client brings a novel structure—say, a securitization of an asset class we haven’t seen before—the platform can ingest and model it without waiting for a software release. This extensibility is what allows a platform to stay current with market innovation rather than constantly playing catch-up.

What This Means in Practice

The architectural decisions in RiskSpan’s Private ABF platform translate directly to operational capabilities. For deal structuring, you can model waterfall variations and see their impact on tranche economics before going to market. For pricing, you can run scenarios against actual loan-level collateral, not simplified pool assumptions. For risk management, you can monitor trigger proximity and project breach timing under stress. For surveillance, you can track every metric that matters, with full audit trails and historical reconstruction.

Private ABF deserves purpose-built infrastructure. RiskSpan’s Private ABF platform delivers it.

Modernizing the Advance: Using Data to Innovate Collateral-Backed Lending

By David Andrukonis & Thomas Pappalardo

Advances haven’t changed much. But the data behind them has.

For decades, the Federal Home Loan Bank System (FHLBanks) has provided reliable, collateralized liquidity to its member institutions, which include banks, credit unions, insurance companies, and CDFIs through FHLBank advances. The model’s value has been proven through multiple credit cycles: members pledge eligible collateral, receive funding, and FHLBanks monitor that collateral to ensure adequate coverage throughout the advance term. In 2024, FHLBanks extended $737 billion to member institutions, with collateral pledged across the system securing advances and other credit products totaling approximately $4.45 trillion.

While the fundamental approach and underwriting of the FHLBank advance program remain sound, the environment has transformed. The collateral backing today’s advances—primarily residential mortgage loans—now generates unprecedented volumes of performance data. Property values can be revalued continuously, payment histories update in real time, geographic risk concentrations can be mapped and stress-tested instantly, and predictive analytics can forecast delinquency probability months in advance.

The Evolution of Collateral Risk Management

Historically, the advance business was built during an era when loan-level data was expensive to collect and difficult to analyze at scale. FHLBanks developed robust monitoring and risk management processes suited to those constraints: periodic reviews, manual sampling, and conservative haircuts compensated for limited visibility between monitoring cycles. These approaches have served the System well for over 90 years, with minimal credit losses even through severe market stress events.

However, the technological landscape has changed significantly. Data processing and management capabilities have advanced at a rapid pace. Transfers that once required manual translation now move through AI-driven smart-mapping tools that provide quality control and transparency. Loan-level data spanning hundreds of fields per loan, including payment status, property values, borrower characteristics, and modification history, is now easily ingested into analytics-ready formats and can be updated monthly.

Analytical tools have advanced and are more accessible and cost-effective. Cloud-based platforms deliver sophisticated analytics such as updated valuations, loan-level forecasts, machine learning-based predictions, and comprehensive stress testing.

FHLBank members and regulatory expectations have also evolved. Members expect data-driven insights and transparency; regulators emphasize quantitative rigor and proactive risk management. Both expect FHLBanks to leverage available tools to enhance risk oversight and delivery safely on its core liquidity mission.

The Era to Modernize Data and Technology for the System

Each FHLBank’s board establishes its own collateral policy, creating significant variability across the eleven-bank system. These differences reflect variations in member risk characteristics, individual risk tolerances, geographic market differences, and diverse methods and vendors for determining collateral lendable values. Key distinctions include eligible collateral types, collateral discounts (“haircuts”), and conditions for collateral delivery. Each FHLBank discounts the reported market or par value of pledged collateral to ensure liquidation value exceeds the value of products being secured, with haircuts depending on collateral type, member credit quality, security method, financial condition, and asset value trends under adverse conditions.

This decentralized approach creates opportunities for advanced technology platforms to standardize risk assessment, manage arbitrage through sophisticated pricing models, enhance collateral valuation precision, and provide comprehensive data analytics that modernize collateral management and advance pricing practices across the system.

What Modern Collateral Analytics Enable

Platforms like RiskSpan’s transform collateral monitoring from periodic assessment to continuous risk management. For FHLBanks, this translates into several powerful capabilities:

Real-Time Collateral Visibility

RiskSpan provides continuous monitoring of pledged collateral across multiple dimensions:

Current performance metrics: Track delinquency rates, payment patterns, and modification activity as they evolve.
Mark-to-market property valuations: Geo-specific house price trends drive updated valuations reflecting current market conditions
Updated loan-to-value ratios: See how LTVs migrate as property values and loan balances change.
Geographic concentration analysis: Understand where collateral is concentrated and how markets are correlating.

This visibility enables proactive conversations with members about their collateral profiles and borrowing capacity.

The chart and table below illustrate how the RiskSpan Platform can immediately summarize geographic concentration and performance data across one FHLBank region (Atlanta’s in this example). The charts below reflect public Agency (Fannie and Freddie) data. But the same analysis can easily and immediately be performed on loan collateral pledged to a FHLBank once the data service is established to maintain that data in the Platform. This is accomplished through an AI-enabled data collection and normalization process.

Exhibit 1: Performance by State – FHLBank Atlanta Region – Agency Data Extracted from RiskSpan Platform – Historical Performance Module

Predictive Risk Assessment

Modern analytics can forecast where risks are heading:

Delinquency probability models identify loans likely to become troubled before they miss payments
Geographic risk assessments flag markets experiencing deteriorating economic conditions
Portfolio stress testing models how collateral would perform under various adverse scenarios
Early warning indicators surface concerning trends while multiple mitigation options remain available

These predictive capabilities allow FHLBanks to move from reactive problem-solving to proactive risk management, enabling earlier intervention and more real-time reporting to regulators.

Granular Analytics for Better Decisions

RiskSpan’s Platform enables analysis at multiple levels—from system-wide exposure down to individual loan characteristics. Credit officers can:

Start with high-level portfolio metrics and drill down into specific concentrations.
Compare collateral quality across members.
Identify specific loans or segments driving portfolio-level trends.
Generate detailed reports for management, regulators, and members.

This granularity supports both risk assessment and member relationship management.

Innovation Opportunities for Managing Advances

Enhanced collateral analytics create opportunities to fundamentally reimagine FHLBank member advance products:

Risk-Based Pricing and Terms

With precise, objective measures of collateral quality, FHLBanks can move toward pricing and structuring advances that reflect actual risk levels:

Differentiated pricing tiers recognize superior collateral quality, incentivizing members to pledge higher-quality collateral and enabling FHLBanks to confidently extend advances across a broader range of risk profiles.
Dynamic advance terms respond to changing collateral conditions, with transparent triggers tied to observable metrics.
Forward-looking eligibility standards incorporate predictive analytics, adjusting concentration limits and eligibility based on real-time market conditions and stress-test performance.

Enhanced Member Value

Modern analytics deliver more value to members:

More efficient collateral usage allows haircuts to be precisely calibrated to actual risk, potentially increasing borrowing capacity.
Faster advance processing results from continuous monitoring and accelerated data processing.
Valuable portfolio insights strengthen member relationships, positioning FHLBanks as strategic partners.

Collateral Transparency and System Resilience in Times of Stress

The Federal Home Loan Bank system is a critical liquidity tool for the national banking system in times of distress. A recent Urban Institute report outlines how significant a role FHLBanks play in reducing the risk of financial crises.

The March 2023 regional bank liquidity events also highlighted the systemic importance of FHLBank liquidity provision. During peak stress, the FHLBank System’s advances outstanding increased by over $300 billion—demonstrating its role as a critical stabilizing force. But this massive, rapid deployment of liquidity required FHLBanks to quickly assess collateral from institutions they might not have previously served extensively, while coordinating with other FHLBanks and government agencies supporting the same institutions. As regional banks sought emergency funding from multiple sources, it exposed challenges in collateral coordination across government regulators and FHLBanks that were proactively intervening. Determining available collateral capacity, avoiding double-pledging, and coordinating lien positions becomes complex when speed is essential.

Enhanced collateral analytics and data management can dramatically improve coordination:

Real-time collateral position visibility allows FHLBanks to instantly see what collateral a member has pledged, its current valuation, and remaining borrowing capacity. When regulators, the Federal Reserve, or other FHLBanks need to understand a troubled institution’s collateral position, RiskSpan can generate comprehensive reports in minutes rather than days.

The examples below (shown for illustrative purposes using public data) address exposure at geographic and servicer level. FHLBanks can run analogous queries on the platform at the member level using their own proprietary data.

Exhibit 2: Query Screenshot: RiskSpan AI MBS Agent Module

Exhibit 3: Performance by Servicer – FHLBank San Francisco – Agency Data Extracted from RiskSpan Platform – Historical Performance Module (via AI MBS Agent)

AI tools can also help identify trends in performance data:

Standardized collateral data management facilitates communication across the FHLBank System and with other government entities. If an institution operates across multiple FHLBank districts and has pledged collateral to different Banks, consistent data standards and analytical frameworks enable those Banks to quickly share information and coordinate responses. Rather than reconciling different valuation methodologies or collateral categorizations during a crisis, all parties work from common data foundations.

Stress scenario analysis becomes critical when evaluating whether to extend emergency liquidity. During March 2023, FHLBanks needed to rapidly assess: How would this institution’s pledged collateral perform if deposit outflows continue? What if property values in their markets decline by 20%? Is the current haircut adequate if market conditions deteriorate further? RiskSpan’s AI-driven MBS Data Agent tool has stress testing capabilities that enable making these assessments in real-time, supporting confident decision-making when hours matter.

Lien priority and collateral allocation transparency helps coordinate among multiple creditors. When an institution has borrowed from both an FHLBank and the Federal Reserve, clear documentation of which specific assets secure which facilities, lien positions, and remaining unencumbered assets is essential. Modern collateral management systems maintain this documentation systematically, reducing confusion and potential disputes during already stressful periods.

Rapid collateral substitution and revaluation capabilities allow FHLBanks to respond dynamically as conditions evolve. If an institution’s collateral quality deteriorates, the technology platform can immediately model how much additional collateral would be needed to maintain existing advance levels, or conversely, whether advance reductions are necessary. This agility protects FHLBank credit quality while maintaining maximum possible support for the troubled institution.

Enhanced collateral analytics don’t just improve routine risk management but serve to strengthen the FHLBank System’s ability to fulfill its countercyclical liquidity role during the moments when that role matters most. Clear collateral visibility, rapid assessment capabilities, and standardized data management transform the FHLBank System’s crisis response from a challenge requiring heroic manual efforts into a systematic capability supported by robust infrastructure.

For policymakers and regulators evaluating the FHLBank System’s role in financial stability, this enhanced capability is crucial. It demonstrates that FHLBanks can rapidly deploy substantial liquidity during stress periods while maintaining strong risk management and coordinating effectively with other parts of the financial safety net. This combination of mission-critical liquidity provision backed by sophisticated risk assessment directly serves the System’s purpose while protecting its safety and soundness. In this age of advanced data and analytics, and with the AI tools available the promise of modernizing FHLBank Advances is tangible and timely.

The Path Forward

Modernizing advance management doesn’t require abandoning proven approaches or taking excessive risk. It means enhancing what works by deploying the technology and data tools that provide deeper insight, earlier warning, and more precise calibration of terms to risk. The journey typically begins with integrating member collateral data into a modern analytics platform, establishing baseline metrics, and developing staff capabilities to interpret and act on enhanced analytics. From there, individual FHLBanks can pilot specific innovations—risk-based pricing, dynamic monitoring with automated alerts, before expanding successful approaches system-wide.

A Strategic Imperative

The Federal Home Loan Bank System faces an evolving competitive and regulatory landscape. Mission scrutiny has intensified, member needs have become more sophisticated, and the technology and data landscape is far more robust. Regulatory expectations emphasize quantitative rigor. In this environment, advances that leverage modern data and analytics ensure FHLBanks remain relevant, competitive, and mission focused.

The technology exists. The data is available. The analytical techniques are proven. What’s required is vision to see beyond traditional approaches and commitment to enhancing a business line that has served the FHLBank System well for generations. Advances and the critical liquidity purpose they serve haven’t changed much. But as data and technology have evolved, the opportunity to enhance them has never been greater. FHLBanks that embrace modern collateral analytics can deliver superior risk management, stronger member relationships, and sustainable competitive advantage—all while staying true to their mission of supporting housing finance and community development.

The data revolution in collateral-backed lending has arrived.

About RiskSpan

RiskSpan delivers a single, intelligent analytics solution for structured finance public and private asset-backed finance investors of any size to confidently make faster, more precise trading and portfolio risk decisions and meet reporting requirements with fewer resources, and less time spent managing multiple vendors and internal solutions. 

Learn more at www.riskspan.com. 

RiskSpan thanks Alanna McCargo of iAM Housing Advisors for her advisory services and contributions to this report.

Build vs. Buy: A Strategic Framework for Private ABF Technology Decisions

Private ABF managers are facing a critical infrastructure decision as they scale: build proprietary technology systems in-house, or partner with an established platform?

This decision has major implications for growth, risk, investor perception, operational efficiency, and long-term competitiveness. And as highlighted at the 2025 Private Credit Technology Summit earlier this year, the industry’s rapid evolution makes this decision more consequential than ever.

Below, I break down the key considerations to help private ABF investors evaluate which approach – or combination of approaches best aligns with your strategy, resources, and ambitions.

The Market Context: Why this Decision Matters More Than Ever

A DLA Piper article summarizing the Summit made one theme clear:
Private credit’s competitive edge is increasingly defined by technology, not just origination and underwriting.

Several market forces are reshaping how firms should think about technology infrastructure:

The private credit universe now spans ABF, corporate credit, IG, HY, specialty finance, and more.

Scaling successfully requires clean data infrastructure, automated workflows, real-time portfolio and risk monitoring, and transparent reporting – capabilities that take significant time and expertise to build from scratch.

LPs are scrutinizing managers based on their data maturity and operational systems, not just portfolio performance. Technology infrastructure is becoming a competitive differentiator in fundraising.

Growth and diversification create enormous operational complexity. Inefficiencies can compound quickly if tech is not architected for scale.

In this environment, the build-versus-buy decision isn’t about technology preferences – it’s about strategic positioning and where you allocate your firm’s limited resources and attention.

When Building In-House Makes Strategic Sense?

Building in-house can be the right choice if it aligns with your core strengths and long-term strategy and you have the resources to execute well.

Building might be right for your firm if:

1. You expect to have ongoing capacity to maintain and evolve systems as your business grows. This includes deep expertise in private ABF workflows, data engineering, collateral management, and performance analytics.

2. Your investment strategy requires highly specialized, proprietary workflows.
For example, if your collateral type or loan structure is so differentiated that no third-party platform can support it without major customization.

3. You have a long time horizon and can absorb slower time-to-value.
Building can take quarters (or years) and often requires multiple rebuilds as the business grows.

4. You’re prepared to shoulder the full cost of development and ongoing maintenance.
This includes engineering headcount, version control, data pipelines, cloud infrastructure, documentation, cybersecurity, and ongoing regulatory adaptation – costs that often exceed initial projections.

Even so, “build” is often harder than it looks.

The Hidden Complexity of Building

Even when building makes strategic sense, firms often underestimate the challenge. ABF data is messy, siloed, and heterogeneous. Legacy spreadsheets and bolt-on tools don’t scale, and homegrown systems tend to break as soon as asset volume or collateral diversity increases. The engineering talent required understands both capital markets and modern data architecture – a rare and expensive combination.

If technology infrastructure isn’t a core competitive differentiator – if your edge is in sourcing, underwriting, or structuring – building can divert critical resources from your highest value activities.

When Partnering Accelerates Your Strategy

For most firms, especially those entering ABF or scaling rapidly, buying and partnering is often the more strategic path.

Partnering might be right for your firm if:

1. You want fast, predictable time-to-value.
A platform built for ABF lets you launch monitoring, reporting, and analytics in weeks instead of quarters – allowing you to deploy capital and focus on deals rather than infrastructure.

2. Your team’s primary value is in origination, structuring, underwriting, or asset management.
Your highest-value people should focus on making credit decisions, not on building and debugging software.

3. You expect rapid AUM growth or expanding asset classes.
A third-party platform offers built-in scalability, flexible data ingestion, and the ability to support new deal types without major reinvestment.

4. You have limited internal engineering infrastructure.
Most private credit firms simply aren’t structured like fintech companies. And they don’t need to be.

5. LPs expect institutional-grade reporting and data transparency.
LPs are now benchmarking managers on data architecture and workflow maturity alongside investment performance. Good technology is no longer a “nice-to-have” – it’s table stakes for institutional capital.

A Framework for Your Decision

Step back and reflect on four key questions:

1. What is your competitive advantage?

If your edge is underwriting, structuring, servicing, or sourcing (i.e., things other than software development) then partnering usually aligns better with your strategy.

2. How quickly do you need to scale?

If speed matters, buying provides immediate infrastructure and eliminates long build cycles.

3. How complex are your investments?

If you’re dealing with multiple asset classes, specialty finance platforms, or varied servicers, you’ll need a system that can evolve faster than most internal builds can.

4. What do your investors expect?

Institutional LPs increasingly demand transparency, data fidelity, and reporting consistency. Technology plays a central role in meeting those expectations.

The Hybrid Approach: Buy the Foundation, Build the Differentiation

We see the same themes across the clients we advise and the ABF platforms we support:

Most private credit and ABF firms benefit from buying and partnering early.
This preserves organizational focus, accelerates operational maturity, and allows firms to stand up institutional-grade workflows much faster.

Some firms may selectively build around a unique competitive edge. But even these tech-savvy firms often choose to buy the foundational plumbing (data ingestion, monitoring, reporting, analytics) and then build their specialized layers on top.

In other words:

Buy the infrastructure.
Build the differentiation.

This is the model we believe will dominate the next decade of private ABF technology evolution.

The decision to build or buy isn’t binary—and it’s not permanent. The firms scaling quickly while maintaining institutional-grade operations are those that make deliberate choices about where to invest their technical resources, based on their competitive positioning and strategic priorities. If you’re evaluating your technology infrastructure options, we are happy to share more about how we’ve helped firms navigate this decision.

How RiskSpan Helped a Credit-Focused Investment Management Firm Transition to Snowflake

A leading investment management firm and recognized leader in structured credit, including asset-backed securities (ABS), mortgage-backed securities (MBS), and other fixed-income sectors, sought RiskSpan’s help transitioning key data processing functions from the data management platform 1010data to Snowflake.

The ability to share data with partners using the same system in which the analytics are performed made the combination of RiskSpan and Snowflake especially attractive. The shift provided significant operational and financial benefits to the client, marking another successful milestone in RiskSpan’s history of helping clients optimize their data management.

Converting Key Functionalities from 1010data to Snowflake

The company had been relying on 1010data for several critical timeseries-based calculations. However, the limitations of the platform—both in terms of speed and cost—prompted them to seek a more modern solution. RiskSpan worked closely with them to replicate and enhance key functionalities using Snowflake. Converted functionalities included:

Timeseries-Based Calculations: We re-engineered these to operate efficiently within Snowflake’s cloud-native architecture, maintaining accuracy while enhancing processing speeds.
fill_nearest: This function retrieves the nearest non-N/A value within a group. It was implemented seamlessly using Snowflake’s window functions, preserving data integrity while boosting performance.
rolling_sum: Snowflake’s SQL capabilities were leveraged to implement the moving sum of valid (non-N/A) values within a window. This provided the company with more responsive and scalable time-series analysis capabilities.
cumulative_run_length: The cumulative run length within a group was translated into Snowflake’s environment using efficient SQL queries, making the entire process faster and more robust.

Integration Capabilities

In addition to replicating 1010data’s core functionalities, the company sought to expand its data capabilities by integrating additional datasets such as Market Data and Home Price Indices (HPI). We showed them how to incorporate and analyze these datasets within Snowflake’s environment, further enhancing their decision-making capabilities.

This cross-functional integration was pivotal in showcasing Snowflake’s ability to streamline complex data workflows. By integrating third-party data directly into their ecosystem, our client can now generate more insightful reports and conduct deeper analysis across multiple datasets without leaving the Snowflake platform.

The Benefits of Transitioning to Snowflake

Our client experienced several immediate and impactful benefits by transitioning from 1010data to Snowflake were immediate and impactful. These included:

Complete Replacement of 1010data: With all critical functionalities successfully converted, the company now can fully discontinue their reliance on 1010data. This eliminates the need for maintaining multiple platforms and simplifies their technology stack.
Significant Cost Savings: Discontinuing 1010data relieved our client of the high costs associated with the platform’s licensing and maintenance fees. Snowflake’s cost-efficient pricing model has already resulted in substantial savings for the company.
Improved Processing Speeds: One of the most noticeable changes has been the drastic improvement in the company’s processing times. Snowflake’s optimized cloud infrastructure provides faster data processing and querying capabilities, significantly reducing time-to-insight.
Access to Full Snowflake Feature Set: Moving to Snowflake has enabled the company to take advantage of features such as data sharing, enhanced security, and elasticity. Snowflake’s built-in scalability ensures our client’s data infrastructure will continue to grow effortlessly as its data needs expand.
Speed and Cost Efficiency: The company has expressed particular satisfaction with both the speed and cost-efficiency of the Snowflake platform. The reduction in data processing time and cost per query has positively impacted its business operations.

Partnering with RiskSpan not only enabled the company to replace 1010data with a more modern and efficient platform, but it has also empowered them to take advantage of Snowflake’s newest, advanced features, including AI.

Contact us to learn how RiskSpan can help you unlock the full potential of your data by guiding you through complex transitions and helping you implement scalable, secure, and cost-effective solutions.

Enhancing a HELOC Lender’s Operations with RiskSpan’s Data as a Service (DaaS)

A leading fintech company specializing in home equity lines of credit (HELOCs), was seeking to optimize the management of its data operations. To accomplish this, the company turned to RiskSpan, a leader in data analytics and financial technology solutions. Through a tailored Data as a Service (DaaS) offering, RiskSpan helped the company improve its HELOC business operations by providing advanced data management and modeling capabilities.

Challenges

The company sought to enhance its HELOC operations in two critical areas:

Data Management and Integration: The company was dealing with complex data sets from multiple sources, including credit bureaus, property data, and customer behavior insights. Integrating and managing this data effectively was crucial for making informed lending decisions.
Risk Assessment and Modeling: Accurate and reliable risk assessment models were necessary for evaluating customer behavior and predicting loan performance. The company required a solution that could model draw behavior and other variables specific to HELOCs.

RiskSpan’s DaaS Solution

RiskSpan’s DaaS offering provided the company with a comprehensive solution tailored to address these challenges. The key components of the solution included:

Advanced Data Integration: RiskSpan’s DaaS platform seamlessly integrated the company’s various data sources, enabling a more streamlined and efficient data management process. This integration allowed the company to better understand their borrowers and make more informed lending decisions.
Enhanced Loan-Level HELOC Pricing and Projections: The client successfully loaded its historical loan performance data onto RiskSpan’s DaaS platform and established a monthly process within the platform’s flexible data warehouse. Using the embedded historical performance tool, the client analyzed loan-level behavior across its portfolio. This enabled the client to generate detailed collateral performance reports for investors and rating agencies, as well as leverage these insights to enhance future projections and loan-level pricing for new loans.
Cost-Effective Data Services: RiskSpan also identified an opportunity to replace the client’s existing data services provider at a significantly reduced cost. By offering a more competitive pricing structure while maintaining high-quality data services, RiskSpan positioned the client to achieve substantial cost savings, making them more competitive in the HELOC market.

Outcomes and Benefits

Implementing RiskSpan’s DaaS solution brought several key benefits:

Improved Decision-Making: With better-integrated data and more accurate modeling of HELOC draw behavior, the client could make more informed lending decisions, ultimately reducing risk and enhancing profitability.
Operational Efficiency: The streamlined data management process allowed the client to operate more efficiently, freeing up resources to focus on core business activities.
Cost Savings: RiskSpan’s competitive pricing enabled the client to cut costs significantly, improving their bottom line and allowing them to reinvest in other areas of the business.

RiskSpan’s Data as a Service solution provided the clients with the tools it needed to optimize its HELOC business. By addressing its data integration challenges, improving risk assessment through advanced modeling, and offering a cost-effective alternative to existing data services, RiskSpan helped the client strengthen its market position and enhance overall business performance.

AI Prompt Structuring — Does it Even Matter?

At the mesh point of human ingenuity and artificial intelligence, the importance of appropriately structured prompts is frequently underestimated. Within this dynamic (and, at times, delicate) ecosystem, the meticulous craftmanship of prompts serves as the linchpin, orchestrating a seamless collaboration between human cognition and machine learning algorithms. Not unlike to a conductor directing an ensemble, judicious prompt structuring lays the foundation for AI systems to synchronize with human intent, thereby facilitating the realization of innovative endeavors. Given the large number of interactions with Large Language Models (LLMs) based on 1:1 digital chats, it is important to carefully prompt gen AI models to generate accurate and tailored outputs.

Gartner predicts that more than 80% of enterprises will have used generative artificial Intelligence (gen AI) or deployed gen AI-enabled applications in production environments by 2026, up from less than 5% in 2023.[1] As gen AI adoption continues to accelerate, understanding proper prompt engineering structures and techniques is becoming more and more important.

With this in mind, we are going to discuss the criticality of the structure of AI prompting to the accuracy of AI outputs. Specifically, we discuss how defining objectives, assigning roles, providing context, specifying the output format, and reviews each play a role in crafting effective prompts.

@Indian_Bronson. *“salmon swimming in a river.”* 15 Mar. 2023. *X(Twitter)*, https://twitter.com/Indian_Bronson/status/1636213844140851203/photo/2. Accessed 3 Apr. 2024

Interacting with LLMs through a chat bot function may result in frustrations as users are faced with outputs that are not on par with their expectations. However, the more detail and clarity given to the model, the more resources it will have to understand and execute the task properly. In this context, “detail and clarity” means:

1. Defining the objective

1. Assigning Roles and Providing context

1. Specifying the output format

1. Reviewing & Refining

1. Define the Objective
Some good questions to ask oneself before providing a prompt to the gen AI include: What needs to be done? What tone does it have to be in? What format do we need? A 2023 Standford University study found that models are better at using relevant information that occurs at the very beginning or the end of the request.[2] Therefore, it is important to generate prompts that are context rich, and concise.

2. Assign Roles and Provide Context
Arguably the most important part of prompting, providing context is critical because gen AI machines cannot infer meanings beyond the given prompts. Machines also lack the years of experience necessary to grasp the sense of what is needed and what is not without some explicit direction. The following principles are important to bear in mind:

Precision and Personalization: Providing detailed context and a clear role enables the AI system to deliver responses that are both accurate and tailored to individual user needs, preferences, and the specificity of the situation.

Delimiters like XML tags: & angle brackets: <> are a great way to separate instructions, data, and examples from one another. Think of XML tags as hash tagging on social media.

For example:

I want to learn about Mortgage Finance and its history

What are some key institutions in the industry?

Efficiency and Clarity in Communication: By understanding its expected role, whether as a consultant, educator, or support assistant, an AI application can adjust its communication style, level of detail, and prioritization accordingly. This alignment not only streamlines interactions but also ensures that the dialogue is efficiently directed towards achieving the user’s goals, minimizing misunderstandings and maximizing productivity.

Appropriateness and Ethical Engagement: Knowledge of the context in which it operates, and the nuance of its role allows an AI to navigate sensitive situations with caution, ensuring that responses are both appropriate and considerate. Moreover, this awareness aids in upholding ethical standards in an AI’s responses — crucial for maintaining user trust and ensuring a responsible use of technology.

3. Specify the output format
In crafting a prompt for AI text generation, specifying the output format is crucial to ensuring that the generated output is not only relevant, but also suitable for the intended purpose and audience or stakeholders. To this end:

Provide clear instructions that include details of the text’s purpose, the audience it’s intended for, and any specific points or information that should be included. Clear instructions help prevent ambiguity and ensure that the AI produces relevant and coherent output.

Set the desired tone, language, and topics so that the output is properly tailored to a business need or setting, whether it is an informative email or a summary of a technical report. Outlining specific topics in combination with language and tone setting aids in generating output that resonates with the stakeholders at the appropriate level of formality and delegates the correct purpose of such output to the end user.

Define constraints (length, count, tools, terminology) to help guide the AI’s text generation process within predetermined boundaries. These constraints ensure that the generated output meets the task’s requirements and is consistent with existing systems or workflows. It also minimizes review time and reduces the possibility of submitting additional prompts.

- Supply output examples. This is a great way to encompass all the above tricks for specifying the output format. Examples serve as reference points for style, structure, and content, helping the AI understand the desired outcome more effectively. By providing a tangible example to the gen AI, a user increases the likelihood of achieving a satisfactory result that aligns with expectations.

4. Review & Refine
Last, but nevertheless important, is to review the prompt before submitting it to the gen AI. Check for consistency of terminology and technical terms usage throughout the prompt and formatting, such as tags and bullet points, to avoid confusion in the responses. Make sure the prompt follows logical flow, avoids repetition and unnecessary information to maintain the desired level of specificity and to avoid skewing the response onto the undesired path.

As users navigate the complexities of AI integration, remembering these prompting structures ensures maximization of AI’s potential while mitigating risks associated with misinformation.

Contact us to learn more about how we are helping our clients harness AI’s capabilities, informed by a strategic and mindful approach.

[1] “Gartner Says More than 80% of Enterprises Will Have Used Generative AI Apis or Deployed Generative AI-Enabled Applications by 2026.” Gartner, 11 Oct. 2023, www.gartner.com/en/newsroom/press-releases/2023-10-11-gartner-says-more-than-80-percent-of-enterprises-will-have-used-generative-ai-apis-or-deployed-generative-ai-enabled-applications-by-2026.

[2] Liu, Nelson F., et al. Lost in the Middle: How Language Models Use Long …, July 2023, cs.stanford.edu/~nfliu/papers/lost-in-the-middle.arxiv2023.pdf.

How RiskSpan and Snowflake Helped a Large Insurance Company Revolutionize Its Data Management

Background

Asset managers are increasingly turning to Snowflake’s cloud infrastructure to address the limitations of outdated databases. Migrating to Snowflake grants them access to a sustainable and secure platform that enables efficient data storage, processing, and analytics. This transition empowers asset managers to streamline operations, improve data accessibility, and reduce costs associated with maintaining on-premises infrastructure.

Client Challenge

A large insurance company’s asset management team was seeking to improve its approach to data management in response to its increasingly complex investment portfolio. The company recognized that transitioning to Snowflake would serve as a foundation for sustainable data analysis for years to come.

Desiring a partner to assist with the transition, the life insurer turned to RiskSpan – a preferred Snowflake partner with substantial experience in database architecture and management.

Specifically, the insurance company sought to achieve the following:

Systems Consolidation: Data stored across multiple transactional systems had contributed to data fragmentation and inefficiencies in data retrieval and analysis. The client sought to establish and maintain a consistent source of asset data for enterprise consumption and reporting.

Improved Reporting Capabilities: Quantifying full risk exposures in fast-moving situations proved challenging, leaving the institution vulnerable to unforeseen market fluctuations. Consequently, the client sought to improve its asset evaluation and risk assessment process by incorporating comprehensive look-through data and classification information. The need for various hierarchical classifications further complicated data access and reporting processes which required streamlining the process of producing ad-hoc exposure reports, which often required several weeks and involved teams of people.

Reduction of Manual Processes: The client needed more automated data extraction processes in order to create exposure reports across different asset classes in a more time-efficient manner with less risk of human error.

Reduction of Infrastructure Constraints: On-premise infrastructure had defined capacity limitations, hindering scalability and agility in data processing and analysis.

RiskSpan’s Approach and Solutions Implemented

Collaborative Partnership: RiskSpan worked closely with the client’s IT, risk management, and analytics teams throughout the project lifecycle, fostering collaboration and ensuring alignment with organizational goals and objectives.

Comprehensive Assessment: Together, we conducted a thorough assessment of the client’s existing data infrastructure, analytics capabilities, and business requirements to identify pain points and opportunities for improvement.

Strategic Planning: Based on the assessment findings, the collective team developed a strategic roadmap outlining the migration plan to the unified data platform, encompassing asset data consolidation, portfolio analytics enhancement, and reporting automation.

Unified Data Platform: Leveraging modern technologies, including cloud-based solutions and advanced analytics tools, RiskSpan orchestrated the integration of various data sources and analytics capabilities. Together, we consolidated asset data from various transactional systems into a unified data platform, providing a single source of truth for comprehensive asset evaluation and risk assessment.

Data Lineage Tracking: The team employed dbt Labs tools to build, validate, and deploy flexible reporting solutions from the Snowflake cloud infrastructure. This enabled the tracking of data lineage, adjustments, and ownership.

Daily Exposure Reporting: Leveraging automated analytic pipelines, we enabled real-time generation of exposure reports across different asset classes, enhancing the client’s ability to make timely and informed decisions.

Automated Data Extraction: We automated the data extraction processes, reducing manual intervention and streamlining data retrieval, cleansing, and transformation workflows.

Hierarchical Classification Framework: We implemented a hierarchical classification framework, providing standardized and consistent data hierarchies for improved data access and reporting capabilities.

Transformative Outcomes

Enhanced Decision-making: Implementing advanced analytics capabilities and exposure reporting empowered our client to make informed decisions more quickly, mitigating risks and capitalizing on market opportunities.

Operational Efficiency: Automation of data extraction, analytics modeling, and reporting processes resulted in significant operational efficiencies, reducing time-to-insight and enabling resource reallocation to strategic initiatives.

Scalability and Agility: The migration to a cloud-based infrastructure provides scalability and agility, allowing our client to adapt quickly to changing business needs and accommodate future growth without infrastructure constraints.

Data Governance and Compliance: The implementation of standardized hierarchical classifications strengthened data governance and compliance, ensuring data consistency, integrity, and regulatory adherence. By leveraging Snowflake’s scalable architecture and advanced features, this large asset manager is now positioned to maneuver both its current and future data landscapes. The implementation of Snowflake not only streamlined data management processes but also empowered the organization to extract valuable insights with unprecedented efficiency. As a result, the asset manager can make data-driven decisions confidently, enhance operational agility, and drive sustainable growth in a rapidly evolving market landscape.

RiskSpan Launches MBS Loan Level Historical Data on Snowflake Marketplace

ARLINGTON, Va., June 18, 2024 – RiskSpan, a leading provider of data analytics and risk management solutions for the mortgage industry, announced today that it has launched MBS Loan Level Historical Data on Snowflake Marketplace. RiskSpan’s MBS Loan Level Historical Data on Snowflake Marketplace enables joint customers to access RiskSpan’s normalized and enriched loan-level data for Fannie Mae, Freddie Mac, and Ginnie Mae mortgage-backed securities.

“We are thrilled to join the Snowflake Marketplace and offer our loan-level MBS data to a wider audience of Snowflake users,” said Janet Jozwik, Senior Managing Director at RiskSpan. “This is a first step in what we believe will ultimately become a cloud-based analytical hub for MBS investors everywhere.”

RiskSpan and Snowflake, the AI Data Cloud company, are working together to help joint customers inform business decisions and drive innovations by enabling them to query the data using SQL, join it with other data sources, and scale up or down as needed. RiskSpan also provides sample code and calculations to help users get started with common metrics such as CPR, aging curves, and S-curves.

“RiskSpan’s launch of a unique blend of enriched data onto Snowflake Marketplace represents a major opportunity for Snowflake customers to unlock new value through data on their business journey,” said Kieran Kennedy, Head of Marketplace at Snowflake. “We welcome RiskSpan to the ecosystem and look forward to exploring how we can support our customers as they look to leverage the breadth of the Snowflake platform more effectively.”

Joint customers can now leverage Loan-Level MBS Data on Snowflake Marketplace, allowing them to access RiskSpan data enhancements, including servicer normalization, refinements, mark-to-market LTV calculations, current coupon. These and other enhancements make it easier and faster for users to perform analysis and modeling.

Snowflake Marketplace is powered by Snowflake’s ground-breaking cross-cloud technology, Snowgrid, allowing companies direct access to raw data products and the ability to leverage data, data services, and applications quickly, securely, and cost-effectively. Snowflake Marketplace simplifies discovery, access, and the commercialization of data products, enabling companies to unlock entirely new revenue streams and extended insights across the AI Data Cloud. To learn more about Snowflake Marketplace and how to find, try and buy the data, data services, and applications needed for innovative business solutions, click here.

About RiskSpan, Inc.

RiskSpan delivers a single analytics solution for structured finance and private credit investors of any size to confidently make faster, more precise trading and portfolio risk decisions and meet reporting requirements with fewer resources, and less time spent managing multiple vendors and internal solutions. Learn more at www.riskspan.com.

The newest, fastest and easiest way to access and analyze Agency MBS data

TL;DR Summary of Benefits

Data normalization and enhancement: RiskSpan’s MBS data on Snowflake normalizes Fannie, Freddie, and Ginnie loan-level data, consolidating everything into one set of field names. It also offers enhanced loan level-data fields, including current coupon, spec pool category, and mark-to-market LTV, which are not available in the raw data from the agencies. The data also includes pool-level factors like pool prefix and pool age, as well as full loan histories not available from the GSEs directly.
Data access and querying: Users access the data in Snowflake using SQL or Python connectors. Snowflake functions essentially as a cloud SQL server that allows for instantaneous data sharing across entities. In just a few clicks, users can start analyzing MBS data using their preferred coding language—no data, ETL, or IT Teams required.
Data merging and analytics: Users can merge the data in Snowflake with other available loan level or macroeconomic data, including interest rates, home prices, and unemployment, for advanced analytics. Users can also project performance, monitor portfolios, and create spec pools, among other features.

CHECK OUT RISKSPAN’S OFFERING ON SNOWFLAKE MARKETPLACE

The Problem

Even though Fannie, Freddie and Ginnie have been making MBS performance data publicly available for years, working with the raw data can be challenging for traders and back-office analysts.

Traders and analysts already have many of the tools they need to write powerful queries that can reveal hidden patterns and insights across different markets – patterns that can reveal lucrative trading opportunities based on prepayment analysis. But one big obstacle often stands in the way of getting the most out of these tools: the data from the agencies is large and unwieldy and is not formatted in a consistent way, making it hard to compare and combine.

What’s more, the Agencies do not maintain full history of published data on the websites for download. Only recent history is available.

The Solution: RiskSpan’s new MBS loan-level historical offering on Snowflake Marketplace

Using RiskSpan’s new MBS Loan-Level Historical Data Offering, MBS traders and analysts can now leverage the power of Snowflake, the leading cloud data platform, to perform complex queries and merge data from multiple sources like never before.

This comprehensive data offering provides a fully normalized view of the entire history of loan-level performance data across Agencies – allowing users to interact with the full $9T Agency MBS market in unprecedented ways.

A list of normalized Fannie and Freddie fields can be found at the end of this post.

In addition to being able to easily compare different segments of the market using a single set of standardized data fields, MBS traders and analysts also benefit from derived and enhanced data, such as current coupon, refinance incentive, current loan-to-value ratio, original specified pool designation, and normalized seller and servicer names.

The use cases are practically limitless.

MBS traders and analystscan track historical prepayment speeds, find trading opportunities that offer relative value, and build, improve, or calibrate prepayment models. They can see how prepayment rates vary by loan size, credit score, geographic location, or other factors. They can also identify pools that have faster or slower prepayments than expected and exploit the differences in price.

Loan originators can see how their loans perform compared to similar loans issued by other originators, servicers, or agencies, allowing them to showcase their ability to originate high-quality loans that command premium pricing.

Enhanced fields provide users with more comprehensive insights and analysis capabilities. They include a range of derived and enhanced data attributes beyond the standard dataset: derived fields useful for calculations, additional macroeconomic data, and normalized field names and enumerations. These fields give users the flexibility to customize their analyses by incorporating additional data elements tailored to their specific needs or research objectives.

Enhanced loan-level fields include:

Refi Incentive: The extent to which a borrower’s interest rate exceeds current prevailing market rates
Spread at Origination (SATO): a representation of the total opportunities for refinancing within a mortgage servicing portfolio. SATO encompasses all potential refinance candidates based on prevailing market conditions, borrower eligibility, and loan characteristics
Servicer Normalization: A standardization of servicer names to ensure consistency and accuracy in reporting and analysis
Scheduled Balance: A helper field necessary to easily calculate CPR and other performance metrics
Spec Pool Type: A designation of the type of spec story on the loan’s pool at origination
Current LTV: a walked forward LTV based on FHFA’s HPI and the current balance of the loan

Not available in the raw data from the agencies, these fields allow MBS traders and analysts to seamlessly project loan and pool performance, monitor portfolios, create and evaluate spec pools, and more.

Access the Data on Your Terms

Traders and analysts can access the data in Snowflake using SQL or Python connectors. Alternatively, they can also access the data through the Edge UI, our well-established product for ad hoc querying and visualization. RiskSpan’s Snowflake listing provides sample queries and a data dictionary for reference. Data can be merged with macroeconomic data from other sources – rates, HPI data, unemployment – for deeper insights and analytics.

The listing is available for a 15-day free trial and can be purchased on a monthly or annual basis. Users don’t need to have a Snowflake account to try it out. Learn more and get started at the Snowflake Marketplace or contact us to schedule a demo or discussion.

CHECK OUT RISKSPAN’S OFFERING ON SNOWFLAKE MARKETPLACE

Fannie/Freddie Normalized Fields

NAME	TYPE	DESCRIPTION
AGE	Number	Loan Age in Months
AGENCY	Varchar	FN [Fannie Mae], FH [Freddie Mac]
ALTDQRESOLUTION	Varchar	Payment deferral type: CovidPaymentDeferral,DisasterPaymentDeferral,PaymentDeferral,Other/NA
BORROWERASSISTPLAN	Varchar	Type of Assistance: Forbearance, Repayment, TrialPeriod, OtherWorkOut, NoWorkOut, NotApplicable, NotAvailable
BUSINESSDAYS	Number	Business Day in Factor Period
COMBINEDLTV	Float	Original Combined LTV
CONTRIBUTION	Float	Contribution of Loan to the Pool, to be used to correctly attribution Freddie Mirror Pools
COUPON	Float	Net Coupon or NWAC in %
CURRBALANCE	Float	Current Balance Amount
CURRENTCOUPON	Float	Primary rate in the market (PMMS)
CURRENTLTV	Float	Current Loan to Value Ratio based on rolled-forward home value calculated by RiskSpan based on FHFA All-Transaction data
CURTAILAMOUNT	Float	Dollar amount curtailed in the period
DEFERRALAMOUNT	Float	Dollar amount deferred
DQSTRING	Varchar	Delinquency History String, left most field in the current period
DTI	Float	Debt to Income Ratio %
FACTORDATE	Date	Performance Period
FICO	Number	Borrower FICO Score [300,850]
FIRSTTIMEBUYER	Varchar	First time home buyer flag Y,N,NA
ISSUEDATE	Date	Loan Origination Date
LOANPURPOSE	Varchar	Loan Purpose: REFI,PURCHASE,NA
LTV	Float	Original Loan to Value Ratio in %
MATURITYDATE	Date	Loan Maturity Date
MICOVERAGE	Float	Mortgage Insurance Coverage %
MOSDELINQ	Varchar	Delinquency Status: Current, DQ_30_Day, DQ_60_Day, DQ_90_Day, DQ_120_Day, DQ_150_Day, DQ_180_Day, DQ_210_Day, DQ_240_Day, DQ_270_Day, DQ_300_Day, DQ_330_Day, DQ_360_Day, DQ_390_Day, DQ_420_Day, DQ_450_Day, DQ_480_Day, DQ_510_Day, DQ_540_Day, DQ_570_Day, DQ_600_Day, DQ_630_Day, DQ_660_Day, DQ_690_Day, DQ_720pls_Day
MSA	Varchar	Metropolitian Statistical Area
NUMBEROFBORROWERS	Number	Number of Borrowers
NUMBEROFUNITS	Varchar	Number of Units
OCCUPANCYTYPE	Varchar	Occupancy Type: NA,INVESTOR,OWNER,SECOND
ORIGBALANCE	Float	Original Loan Balance
ORIGSPECPOOLTYPE	Varchar	Spec Story of the pool that the loan is a part of. Please see Spec Pool Logic in our linked documentation
PERCENTDEFERRAL	Float	Percentage of the loan balance that is deferred
PIW	Varchar	Property Inspection Waiver Type: Appraisal,Waiver,OnsiteDataCollection, GSETargetedRefi, Other,NotAvailable
POOLAGE	Number	Age of the Pool
POOLID	Varchar	Pool ID

12 3 4 5 6

AI Isn’t Coming to Structured Finance. It’s Already Here.

The Data Model That Powers Private ABF: Why Purpose-Built Architecture Changes Everything

Modernizing the Advance: Using Data to Innovate Collateral-Backed Lending

Build vs. Buy: A Strategic Framework for Private ABF Technology Decisions

How RiskSpan Helped a Credit-Focused Investment Management Firm Transition to Snowflake

Converting Key Functionalities from 1010data to Snowflake

Integration Capabilities

The Benefits of Transitioning to Snowflake

Enhancing a HELOC Lender’s Operations with RiskSpan’s Data as a Service (DaaS)

Challenges

RiskSpan’s DaaS Solution

Outcomes and Benefits

AI Prompt Structuring — Does it Even Matter?

How RiskSpan and Snowflake Helped a Large Insurance Company Revolutionize Its Data Management

Background

Client Challenge

RiskSpan’s Approach and Solutions Implemented

Transformative Outcomes

RiskSpan Launches MBS Loan Level Historical Data on Snowflake Marketplace

The newest, fastest and easiest way to access and analyze Agency MBS data

The Problem

The Solution: RiskSpan’s new MBS loan-level historical offering on Snowflake Marketplace

Access the Data on Your Terms

Fannie/Freddie Normalized Fields

Company

Products

Security & Compliance