Linkedin    Twitter   Facebook

Get Started
Log In

Linkedin

Blog Archives

Will a Rising VQI Materially Impact Servicing Costs and MSR Valuations?

VQI-GraphVQI-Current-Layers-September-2021

RiskSpan’s Vintage Quality Index computes and aggregates the percentage of Agency originations each month with one or more “risk factors” (low-FICO, high DTI, high LTV, cash-out refi, investment properties, etc.). Months with relatively few originations characterized by these risk factors are associated with lower VQI ratings. As the historical chart above shows, the index maxed out (i.e., had an unusually high number of loans with risk factors) leading up to the 2008 crisis.

RiskSpan uses the index principally to fine-tune its in-house credit and prepayment models by accounting for shifts in loan composition by monthly cohort.

Will a rising VQI translate into higher servicing costs?

The Vintage Quality Index continued to climb during the third quarter of 2021, reaching a value of 85.10, compared to 83.40 in the second quarter. The higher index value means that a higher percentage of loans were originated with one or more defined risk factors.

The rise in the index during Q3 was less dramatic than Q2’s increase but nevertheless continues a trend going back to the start of the pandemic. The increase continues to be driven by a subset of risk factors, notably the share of cash-out refinances and investor properties (both up significantly) and high-DTI loans (up modestly). On balance, fewer loans were characterized by the remaining risk metrics.

What might this mean for servicing costs?

Servicing costs are highly sensitive to loan performance. Performing Agency loans are comparatively inexpensive to service, while non-performing loans can cost thousands of dollars per year more — usually several times the amount a servicer can expect to earn in servicing fees and other ancillary servicing revenue.

For this reason, understanding the “vintage quality” of newly originated mortgage pools is an element to consider when forecasting servicing cash flows (and, by extension, MSR pricing).

Each of the risk layers that compose the VQI contributes to marginally higher default risk (and, therefore, a theoretically lower servicing valuation). But not all risk layers affect expected cash flows equally. It is also important to consider the VQI in relationship to its history. While the index has been rising since the pandemic, it remains relatively low by historical standards — still below a local high in early 2018 and certainly nowhere near the heights reached leading up to the 2008 financial crisis.

A look at the individual risk metrics driving the increase would also seem to reduce any cause for alarm. While the ever-increasing number of loans with high debt-to-income ratios could be a matter of some concern, the other two principal contributors to the overall VQI rise — loans on investment properties and cash-out refinances — do not appear to jeopardize servicing cash flows to the same degree as low credit scores and high DTI ratios do.

Consequently, while the gradual increase in loans with one or more risk factors bears watching, it likely should not have a significant bearing (for now) on how investors price Agency MSR assets.

VQI-Risk-Layer-All-Issued-Loans-September-2021VQI-Risk-Layers-FICO-660-September-2021

VQI-LTV-80-Shared-of-Issued-Loans-September-2021 VQI-Debt-to-Income-45-Share-of-Issued-Loans-September-2021 VQI-Adjustabel-Rate-Share-of-issued-Loans-September-2021 VQI-Loans-with-Subordinate-Financing-September-2021-1024x399.png

Population assumptions:

  • Monthly data for Fannie Mae and Freddie Mac.
  • Loans originated more than three months prior to issuance are excluded because the index is meant to reflect current market conditions.
  • Loans likely to have been originated through the HARP program, as identified by LTV, MI coverage percentage, and loan purpose, are also excluded. These loans do not represent credit availability in the market as they likely would not have been originated today but for the existence of HARP.

Data assumptions:

  • Freddie Mac data goes back to 12/2005. Fannie Mae only back to 12/2014.
  • Certain fields for Freddie Mac data were missing prior to 6/2008.

GSE historical loan performance data release in support of GSE Risk Transfer activities was used to help back-fill data where it was missing.

An outline of our approach to data imputation can be found in our VQI Blog Post from October 28, 2015.


RiskSpan Wins Risk as a Service Category for Second Consecutive Year, Leaps 12 Spots in RiskTech100® 2022 Ranking

RiskSpan’s Edge Platform, a leadingRiskTech 100 provider of risk analytics, data, and behavioral modeling to the structured finance industry, is the “Risk as a Service” category winner for the second consecutive year in Chartis Research’s prestigious RiskTech100® ranking of the world’s 100 top risk technology firms. 

The win accompanies a 12-point improvement in RiskSpan’s overall ranking, placing the firm among the year’s most significant movers.  

“RiskSpan’s continued growth and ongoing partnership strategy have made it one of the big risers in the rankings this year,” said Phil Mackenzie, Research Principal at Chartis Research. “Its strength in securitization and analytics as a service is reflected in its 12-point jump.” 

Licensed by some of the largest asset managers, broker/dealers, hedge funds, mortgage REITs and insurance companies in the U.S., Edge is a one-stop shop for research, analytics, pricing, risk metrics, and reporting. Edge’s cloud-native infrastructure scales as individual client needs change and is supported by RiskSpan’s unparalleled team of mortgage and structured finance experts.  

“This year’s award reflects a year marked by an unprecedented wave of enhancements to our risk platform, noted Bernadette Kogler, RiskSpan’s co-founder and CEO. “Our loan-level analytics has been a hit, while our fully managed risk option continues to tailor scalable offerings to individual client needs. Our best-in-class portfolio analytics for structured products are fast becoming the talk of the industry.”


About RiskSpan 

RiskSpan offers end-to-end solutions for data management, risk analytics, and visualization on a highly secure, fast, and fully scalable, cloud-native platform that has earned the trust of the mortgage and structured finance industry’s largest firms. Combining the strength of subject matter experts, quantitative analysts, and technologists, RiskSpan’s Edge Platform integrates a range of datasets – structured and unstructured – and off-the-shelf analytical tools providing users with powerful insights and a competitive advantage. Learn more at www.riskspan.com.


About Chartis Research: 

Chartis Research is the leading provider of research and analysis on the global market for risk technology. It is part of Infopro Digital, which owns market-leading brands such as Risk and WatersTechnology. Chartis’ goal is to support enterprises as they drive business performance through improved risk management, corporate governance and compliance, and to help clients make informed technology and business decisions by providing in-depth analysis and actionable advice on virtually all aspects of risk technology. 


Non-Linear Paths to Leadership: RiskSpan to Join Structured Finance Association WiS NextGen Panel

On Tuesday, November 16th RiskSpan CEO Bernadette Kogler joined fellow Women in Securitization NextGen panelists Beth O’Brien, Adama Kah, and Libby Cantrill, CFA to discuss Seizing Opportunites at Every Stage of Your Career, moderated by Structured Finance Association President Kristi Leo.

Watch here: https://structuredfinance.org/women-in-securitization/ Wis NextGen:Non-Linear Paths to Leadership

Topics included:

  • Why it’s essential to take risks in your career
  • How to seize opportunities and take on challenges
  • Leveraging an entrepreneurial spirit when exploring possibilities that don’t align with a preset career path – and taking that leap


RiskSpan, Arete Risk Advisors Announce Strategic Consulting Partnership

AreteRiskSpan, a leading provider of data and analytics solutions to the mortgage industry, has announced a partnership with Arete Risk Advisors, LLC, to complement RiskSpan’s existing team of data science, modeling, and financial engineering consultants.  A woman-owned firm boasting a deep bench of experienced housing finance professionals, Arete delivers unparalleled expertise in applying operations, information technology, governance, risk management, and internal controls best practices to every aspect of home lending.  Arete is led by managing partner Patricia Black, an industry-leading executive in home lending. Prior to founding Arete, Patricia served as Fannie Mae’s Chief Audit Executive, Chief of Staff at Caliber Home Loans, the Head of Sales and Operations at SoFi, and a Senior Manager at KPMG Consulting/BearingPoint.    “I’m very excited to be involved with a growing woman-owned business while simultaneously expanding our own advisory offering,” said Bernadette Kogler, Co-Founder and CEO of RiskSpan. “Arete’s emphasis on delivering top-qualify mortgage compliance, controls, governance, and operations services creates a natural synergy with RiskSpan’s data and modeling capabilities. This partnership promises to benefit clients of both firms.”  Patricia Black added, “the opportunity to grow with Bernadette and the RiskSpan team to expand women-owned businesses in the home lending space is inspiring and I am excited about contributing to the continued success of Bernadette and her team.”  Learn more about Arete’s range of services at www.areteriskadvisors.com. Questions about the firm may be directed to info@areteriskadvisors.com.  About RiskSpan  RiskSpan offers end-to-end solutions for data management, risk analytics, and visualization on a highly secure, fast, and fully scalable, cloud-native platform that has earned the trust of the mortgage and structured finance industry’s largest firms. Combining the strength of subject matter experts, quantitative analysts, and technologists, RiskSpan’s Edge Platform integrates a range of datasets – structured and unstructured – and off-the-shelf analytical tools providing users with powerful insights and a competitive advantage. Learn more at www.riskspan.com. 


Senior Housing Wealth Exceeds Record $9.57 Trillion

Homeowners 62 and older saw their housing wealth grow by 3.7 percent in the second quarter to a record $9.57 trillion, according to the latest quarterly release of the NRMLA/RiskSpan Reverse Mortgage Market Index.

For a comprehensive commentary, please see NRMLA’s press release.

How RiskSpan Computes the RMMI

To calculate the RMMI, RiskSpan developed an econometric tool to estimate senior housing value, mortgage balances, and equity using data gathered from various public resources. These resources include the American Community Survey (ACS), Federal Reserve Flow of Funds (Z.1), and FHFA housing price indexes (HPI). The RMMI represents the senior equity level at time of measure relative to that of the base quarter in 2000.[1] 

A limitation of the RMMI relates to Non-consecutive data, such as census population. We use a smoothing approach to estimate data in between the observable periods and continue to look for ways to improve our methodology and find more robust data to improve the precision of the results. Until then, the RMMI and its relative metrics (values, mortgages, home equities) are best analyzed at a trending macro level, rather than at more granular levels, such as MSA.


[1] There was a change in RMMI methodology in Q3 2015 mainly to calibrate senior homeowner population and senior housing values observed in 2013 American Community Survey (ACS).


Top 10 National Mortgage Servicer: MSR Pricing Model Review, Analysis and Enhancements

One of the nation’s leading mortgage lenders had recently acquired several large MSR portfolios and required assistance reviewing, documenting and recommending enhancements to the underlying assumptions of the model used to price the MSR portfolios at acquisition.

Requiring review and documentation included collateral assumptions, cost and revenue assumptions, and prepayment (CDR/CRR/CPR) assumptions.

The Solution

RiskSpan comprehensively analyzed the cash flow impact of each major assumption (e.g., CDR/CRR/CPR, servicing advances, fees, cost) — the collateral assumptions in the model as well as documented forecast vs. actual outcomes.

RiskSpan worked in concert with the servicer’s finance and pricing teams to collect and analyze roll rates and to forecast actual loan-level data around losses, servicing advances, servicing fees, ancillary fees, PIF, and scheduled principal payments.  

Deliverables 

A comprehensive pricing model validation report that included the following:

  • Consolidated CDR-, CRR-, CPR-related pricing model data, including balance, delinquency status, recapture, scheduled payments, default, etc. for all acquired portfolios. The resulting dataset could be used both for deal tracking and pricing model validation 
  • Documentation of the calculation and location of pricing model fields.
  • Reconciliation of the different methods for calculating CDR, CRR, and CPR.
  • Deep dives into model predictions of short sales and foreclosure turn-times
  • Loan-state transition model forecasts and comparison of the model variables between two version of the forecast, including shift analyses.
  • Drivers of forecast variance. 
  • Identification of dials responsible for short sale and foreclosure turn forecast shifting.
  • SAS-based streamlined process for comparing model variables for sub-segment and sub-models in loan state
  • Transition Model:  Incorporation of actual and forecast into pricing models to compare with original pricing model cash flow results for acquired portfolios
  • Creation and standardization of the pricing model validation report output.
  • Automation of reporting.  
  • Improvement of the process by creating a calculation template that could be easily replicated for other portfolios. 
  • Documentation of the validation process and comprehensive review of the validation results with the servicer’s risk team, finance team and pricing team management.


Applying Few-Shot Learning Techniques to Mortgage Data

Few-shot and one-shot learning models continue to gain traction in a growing number of industries – particularly those in which large training and testing samples are hard to come by. But what about mortgages? Is there a place for few-shot learning where datasets are seemingly so robust and plentiful? 

 

A growing body of evidence suggests that the high dimensionality of mortgage data spaces may actually make them ideal candidates for few-shot learning. 

 

Suhrud Dagli and Jing Liu present the latest installment in RiskSpan’s Data & Machine Learning Workshop series. Suhrud and Jing share examples of how they are using few-shot learning techniques in prepayment modeling and in automating quality control checks on uploaded mortgage data. 

 


Featured Speakers

Suhrud Dagli

Co-Founder and CIO, RiskSpan

Jing Liu

Senior Analyst, RiskSpan


EDGE: QM vs Non-QM Prepayments

Prepayment speeds for qualified mortgages (QM loans) have anecdotally been faster than non-QM loans. For various reasons, the data necessary to analyze interest rate incentive response has not been readily available for these categories of mortgages.

In order to facilitate the generation of traditional refinancing curves (S-curves) over the last year, we have normalized data to improve the differentiation of QM versus non-QM loans within non-agency securities.

Additionally, we isolated the population to remove prepay impact from loan balance and seasoning.

The analysis below was performed on securitized loans with 9 to 36 months of seasoning and an original balance between 200k and 500k. S-curves were generated for observation periods from January 2016 through July 2021.

Results are shown in the table and chart below.

Edge-QM-vs-Non-QM-Refi-Incentive


Edge-QM-vs-Non-QM-Refi-Incentive

For this analysis, refinance incentive was calculated as the difference between mortgage note rate and the 6-week lagged Freddie Mac primary mortgage market survey (PMMS) rate. Non-QM borrowers would not be able to easily refi into a conventional mortgage. We further analyzed the data by examining prepayments speeds for QM and non-QM loans at different level of SATO. SATO, the spread at origination, is calculated as the difference between mortgage note rate and the prevailing PMMS rate at time of loan’s origination.

Edge-QM-vs-Non-QM-Refi-Incentive

Using empirical data maintained by RiskSpan, it can be seen the refinance response for QM loans remains significantly faster than Non-QM loans.

Using Edge, RiskSpan’s data analytics platform, we can examine any loan characteristic and generate S-curves, aging curves, and time series. If you are interested in performing historical analysis on securitized loan data, please contact us for a free demonstration.


RiskSpan Named to Inaugural STORM50 Ranking by Chartis Research – Winner of “A.I. Innovation in Capital Markets”

Chartis Research has named RiskSpan to its Inaugural “STORM50” Ranking of leading risk and analytics providers. The STORM report “focuses on the computational infrastructure and algorithmic efficiency of the vast array of technology tools used across the financial services industry” and identifies industry-leading vendors that excel in the delivery of Statistical Techniques, Optimization frameworks, and Risk Models of all types.

STORM50

RiskSpan’s flagship Edge Platform was a natural fit for the designation because of its positioning squarely at the nexus of statistical behavioral modeling (specifically around mortgage credit and prepayment risk) and functionality enabling users to optimize trading and asset management strategies.  Being named the winner of the “A.I. Innovation in Capital Markets” solutions category reflects the work of RiskSpan’s vibrant innovation lab, which includes researching and developing machine learning solutions to structured finance challenges. These solutions include mining a growing trove of alternative/unstructured data sources, anomaly detection in loan-level and other datasets, and natural language processing for constructing deal cash flow models from legal documents.

Learn more about the Edge Platform or contact us to discuss ways we might help you modernize and improve your mortgage and structured finance data and analytics challenges.


Automating Compliance Risk Analytics

 Recorded: August 4th | 1:00 p.m. EDT

Completing the risk sections of Form PF, AIFMD, Open Protocol and other regulatory filings requires submitters to first compute an extensive battery of risk analytics, often across a wide spectrum of trading strategies and instrument types. This “pre-work” is both painstaking and prone to human error. Automating these upstream analytics greatly simplifies life downstream for those tasked with completing these filings.

RiskSpan’s Marty Kindler walks through a process for streamlining delta equivalent exposure, 10 year bond equivalent exposure, DV01/CS01, option greeks, stress scenario impacts and VaR in support not only of downstream regulatory filings but of an enhanced, overall risk management regime.


Featured Speaker

Martin Kindler

Managing Director, RiskSpan


Get Started
Log in

Linkedin   

risktech2024