Linkedin    Twitter   Facebook

Get Started
Log In

Linkedin

Articles Tagged with: RS Edge
Home / Blog Archives

How Are Ginnie’s New RG Pools Performing?

In February of this year, the Ginnie Mae II program began guaranteeing securities backed by pools of mortgages previously bought out of Ginnie Mae securities because of delinquency. In order to qualify for these new re-performing pools (known as “RG pools”) a loan must meet two (related) conditions: 

  • Borrower has made at least six months of timely payments prior to pool issuance. 
  • Pool issue date is at least 210 days from when the mortgage was last delinquent. 

The novelty of RG pools raises questions about their composition and performance relative to other Ginnie Mae pools. While it remains too early to make many conclusive statements, a preliminary look at the prepayment data indicates speeds somewhere between those of similar vintage Ginnie Mae multi and custom pools, with typical variability from servicer to servicer.  

In this post, we discuss the prepayment behaviors we have observed over the first seven months of RG pool securitization, issuance patterns, and collateral characteristics. 

Prepayments 

Latest September prepayment prints show that RG pools’ speeds generally fell in between those of similar coupon/vintage multi and custom pools.  Below charts shows that 2015/2016 3.5% RG pools prepaid at around 37-38 CPR in September, a couple of CPR slower than similarly aged multi pools and almost 10 CPR faster than custom pools.  

Prepayments for G2 3.5% RG, Custom and Multi Pools by Vintages, September Factor Month Prepayments for G2 3.5% RG Custom and Multi Pools by vintages, Sept FactorMonthNote: Loan level data

Below, we plot S-curves for 49 to 72 wala RG loans against S-curves for similarly aged multi and other custom loans from April to September factor months.  Speeds for RG loans with 25 to 100 bp of rate incentives have prepaid in mid-30s CPRs (Green line in below figure).  During the same period, similar multi pools have prepaid 5 to 8 CPR faster (blue line) than RG pools while similar custom pools have prepaid around 5 CPR slower (black line).  We also overlaid a s-curve for 7 to 18 wala G2 multi pools as a comparison (orange line).

S-curves for RG, Custom and Multi Pools (49 to 72 WALA) April to September Factor Months 
GNMA PoolNote: Loan level data, orange line is the s-curve for 7-18 wala G2 multi pools with a one-year lookback period 

Not surprisingly, prepayment behavior differs by servicer. Wells-serviced RG pools that are seasoned 49 to 72 months with 25 to 100 bp of rate incentives appear to be prepaying in low 30s CPRs (black line in below figure).  Similar loans from Penny Mac are prepaying 5 to 10 CPR faster, which tends to be the case for non-RG loans as well. 

S-curves for RG loans by servicers, 49 to 72 WALA, April to September Factor MonthsGNMA PoolsNote: Loan level data 

While the re-performing loans that are being securitized into RG pools are already seasoned loans, prepayments have been increasing as pool seasons.  For example, one-month old RG 3.5% pools have prepaid at 27 CPR while 6- and 7-month 3.5% pools prepaid at 45-50 CPR (black line below). In addition, overall prepayment speeds for same-pool-age 3.0%, 3.5%, and 4.0% have been on top of each other. 

 Prepayments for RG 3.0%, 3.5% and 4.0% Pools by Pool Age, March to September 2021 GNMA PoolsNote: only showing data points for cohorts with more than 50 loans

Issuance Volume 

Following a brief ramp-up period in February and March, issuance of RG pools has averaged around $2 billion (and roughly 300 pools) per month for the past five months (see Issuance chart below). The outstanding UPB of these pools stands at nearly $11 billion as of the September factor month. 

GNMA PoolsNote: RiskSpan uses reporting month as a factor month. For this chart, we adjust our factor date by one month to match the collection period.

RG pools already account for a sizable share of Ginnie II custom issuance, as illustrated in the following chart, making up 18% of G2 custom issuance and 3% of all G2 issuance since April.

GNMA PoolsNote: RiskSpan uses reporting month as a factor month. For this chart, we adjust our factor date by one month to match the collection period. 

RG Pool Characteristics 

Nearly all of RG pool issuance has been in 3.0% to 4.5% coupons, with a plurality at 3.5%. As of the September factor month, almost $4 billion (37%) of the outstanding RG pools are in 3.5% coupons. The 4% coupon accounted for the next-largest share–$2.5 billion (23%)—followed by $2.3 billion in 3.0% (20.9%) and $1.3 billion in 4.5% (11.8%). 

RG Pool Outstanding Amount by Coupon — September Factor Month GNMA Pools

 The following table compares the characteristics of RG pools issued since February with those of G2 single-family custom and multi pools issued during the same period.  The table highlights some interesting differences: 

  • Issuance of RG pools seems to be concentrated in higher coupons (3% to 4%) compared to issuances for G2 custom pools (concentrated on 2.5% and 3.0%) and G2 multi-lender pools (concentrated on 2.0% and 2.5%). 
  • Loan sizes in RG pools tend to fall between those of G2 customs and smaller than G2 multis.  For example, WAOLS for 3.5% RG pools is around 245k and is around 50k smaller than multi pools and 30k larger than other custom pools. 
  • RG pools consist almost exclusively of FHA loans while G2 multis have a much higher share of VA loans.  Almost 98% of 3.5% RG loans are FHA loans. 

 G2 RG vs. G2 Custom and G2 Multi (pools issued since February), Stat as of September Factor Month GNMA Pools

Wells Fargo and Penny Mac are far and away the leaders in RG issuance, accounting collectively for 62% of outstanding RG pools.  

RG Pools by Servicer, September Factor Month GNMA Pools

 How to Run RG Pools in Edge Perspective 

Subscribers to Edge Perspective can run these comparisons (and countless others) themselves using the “GN RG” pool type filter. The “Custom/Multi-lender” filter can likewise be applied to separate those pools in G2SF. 

Contact Us

Contact us if you are interested in seeing variations on this theme. Using Edge, we can examine any loan characteristic and generate an S-curve, aging curve, or time series.

Value Opportunities in Private-Label Investor Loan Deals

The supply of investor loan collateral in private securitizations has surged in 2021 and projects to remain high (more on this below). To gain an informational edge while selecting bonds among this new issuance, traders and investors have asked RiskSpan for data and tools to dissect the performance of investor loans. Below, we first show the performance of investor loans compared to owner-occupied loans, and then offer a glimpse into a few relative value opportunities using our data and analytics platform, Edge.

As background, the increase of investor loan collateral in PLS was spurred by a new FHFA policy, recently suspended, that capped GSE acquisitions of investor and second home loans at 7% of seller volume. This cap forced originators to explore private-label securitization which, while operationally more burdensome than GSE execution, has been more profitable because it bypasses the GSEs’ high loan-level pricing adjustments. Now that this difficult but rewarding PLS path has been more widely traveled, we expect it to become more efficient and to remain popular, even with the GSE channel reopening.

Subsector Performance Comparison: Investor Vs. Owner-Occupied Loans

Investor Loans Promise Longer Collection of Above-Market Rates

Compared to owner-occupants, investors have historically paid above-market mortgage rates for longer periods before refinancing. Figure 1 shows the prepayment rates of investors vs. owner-occupants as a function of refinance incentive (the borrower’s note rate minus the prevailing mortgage rate). As their flatter “s-curve” shows, the rise in investor prepayments as refinance incentive increases is much more subdued than for owner-occupants.

Crucially, this relationship is not fully explained by higher risk-based pricing premiums on investor loans. Figure 2 shows the same comparison as Figure 1 but only for loans with spreads at origination (SATO) between 50 and 75 bps. The categorical difference between owner-occupied and investor prepay speeds is partially reduced but clearly remains. We also tried controlling for property type, but the difference persists. The relative slowness of investors may result from investors spreading their attention across many elements of their P&L besides interest expense, from higher underwriting obstacles for a rental income-driven loan, and/or from lenders limiting allocation of credit to the investor type.

While we plot these graphs over a five-year lookback period to balance desires for recency and sample size, this relationship holds over shorter and longer performance periods as well.

Figure 1: The Investor Loans S-Curve is Significantly Flatter Than the Owner-Occupied Curve
Investor s-curve vs. owner-occupied s-curve. Includes prime credit, no prepayment penalty, original loan size $200K-$400K, ages 6-48 months for the past 5yr period performance.

The Investor Loans S-Curve is Significantly Flatter Than the Owner-Occupied Curve

Source: CoreLogic’s Private-Label RMBS Collateral Dataset, RiskSpan. Note: because the increase in private-label investor loan volume is coming from Agency cutbacks, the historical performance of investor loans within both Agency and private-label datasets are relevant to private-label investor loan future performance. In this analysis we show private-label data because it straightforwardly parses voluntary prepays vs. defaults, which of course is a critical distinction for PL RMBS investors. Nonetheless, where applicable, we have run the analyses in both datasets, each of which corroborates the performance patterns we show.

Figure 2: Even Controlling for SATO, The Investor vs. Owner-Occupied S-Curve Difference Persists Even Controlling for SATO, The Investor vs. Owner-Occupied S-Curve Difference Persists Same as Figure 1 but includes only loans with SATO between 50-75 bps Source: CoreLogic, RiskSpan

Investor Loans Pose Comparable Baseline Risk, Greater Downside Risk to Credit Investors

Credit performance of investor loans has been worse than owner-occupied loans during crises, which justifies a pricing premium. During benign periods, investor loans have defaulted at similar or lower rates than owner-occupied loans – presumably due to more conservative LTVs, FICOs and DTIs among the investor loan type – and have therefore been profitable for credit investors during these periods. See Figure 3.

Figure 3: Investor Loans Have Defaulted at Greater Rates During Crises and Similar Rates in Other Periods vs. Owner-Occupied Loans Default rates over time, investor loans vs. owner-occupied. Includes prime credit, ages 12-360 months. Investor Loans Have Defaulted at Greater Rates During Crises and Similar Rates in Other Periods vs. Owner-Occupied Loans Source: CoreLogic, RiskSpan

Relative Value Opportunities Within Investor Loans

California Quicker to Refinance California has the largest share of U.S. investor mortgages, as it does with all residential mortgages. California borrowers, both investors and owner-occupieds, have exhibited a steeper response to refinance incentives than have borrowers in other states. Figure 4 shows the comparison focusing on investors. While historical home price appreciation has enabled refinances in California, it has done the same in many states. Therefore, the speed differences point to a more active refinance market in California. All else equal, then, RMBS investors will prefer less California collateral.

Figure 4: California Prepays Significantly Faster In the Money Investor s-curves bucketed by geography (California vs. Other). Includes prime credit, no prepayment penalty, original loan size $200k-$400k, ages 6-48 months for the past 3yr performance period. California Prepays Significantly Faster In the Money Source: CoreLogic, RiskSpan

For AAA Investors, Limited-Doc Investor Loans May Offer a Two-Sided Benefit: They Buoy Premium Bonds, and a Small Sample Suggests They Lift Discount Bonds, Too

Limited-doc investor loans offer senior tranche holders the chance to earn above-market rates for longer than full-doc investor loans, a relative edge for premium bonds (Figure 5). This is intuitive; we would expect limited-doc borrowers to face greater obstacles to refinancing. This difference holds even controlling for spread at origination. Based on a smaller sample, limited-doc investor loans have also turned over more (see greater prepay rates in the negative refinance incentive bucket). This may result from a correlation between limited documentation and more rapid flipping into the rising HPI environment we have had nationally throughout the past seven years. If so, this would mean that limited-doc investor loans also help discount bonds, relative to full-doc investor loans, accelerate repayments at par.

Because limited-doc investor loans are rare in the RMBS 2.0 era, we widened the performance period to the past seven years to get some sample in each of the refinance incentive buckets. Nonetheless, with all the filters we have put on to isolate the effect of documentation type, there are only a few hundred limited-doc investor loans in the negative refinance incentive buckets.

Figure 5: Limited-Doc Investor Loans Have Prepaid Slower In-The-Money and Faster Out-of-the-Money Investor s-curves bucketed by doc type. Includes prime credit, no prepayment penalty, original loan size $400K-$800K, ages 6-48 months, SATO 25-125bps for the past 7yr performance period. Limited-Doc Investor Loans Have Prepaid Slower In-The-Money and Faster Out-of-the-Money Source: CoreLogic, RiskSpan

Size Affects Refi Behavior – But Not How You Think

An assumption carried over from Agency performance is that rate-driven prepays get likelier as loan size increases. This pattern holds across conforming loan sizes, but then reverses and refinance response gets flatter again as balances cross $800K. This is true for investor and owner-occupied loans in both Agency and private-label loan data, though of course the number of loans above $800K in the Agency data is small. Figure 6 shows this pattern for private-label investor loans. As shown, in-the-money prepayments are slowest among loans below $200K, as we would expect. But despite their much higher motivation to refinance, loans above $800K have similar S-curves to loans of just $200K-$400K.

The SATO is generally a few basis points higher for these largest loans, but this does not explain away the speed differences. Figure 7 shows the same comparison as Figure 6 except only for loans with SATO between 50-75 bps. Except for a slightly choppier graph because of the reduced sample size, the same rank-ordering is evident. Nor does controlling for property type or geography remove the speed differences. The largest loans, we conclude, have fewer credit alternatives and/or face more stringent underwriting hurdles than smaller loans, hampering their refi rates.

Rate refinances are fastest among the mid-sized loans between $400K-$600K and $600K-$800K. That these last two groups have similar S-curves – despite the greater dollar motivation to refinance for the $600K-$800Kgroup – suggests that the countervailing effect of lower ability to find refinancing outlets is already kicking in for the $600K-$800K size range.

All of this means that high-balance collateral should be more attractive to investors than some traditional prepayment models will appreciate.

Figure 6: The Largest Investor Loans Refinance Slower Than Medium-Sized
Investor s-curves bucketed by loan size. Includes prime credit, no prepayment penalty, ages 6-48 months for the past 5yr performance period.

The Largest Investor Loans Refinance Slower Than Medium-Sized

Source: CoreLogic, RiskSpan

Figure 7: Controlling For SATO, Largest Investor Loans Still Refinance Slower Than Medium-Sized
Same as Figure 4 but includes only loans with SATO between 50-75 bps

Controlling For SATO, Largest Investor Loans Still Refinance Slower Than Medium-Sized

Source: CoreLogic, RiskSpan

Preliminarily, Chimera Has Lowest Stressed Delinquencies of Top Investor Shelves

For junior-tranche, credit-exposed investors in the COVID era, 60-day-plus delinquencies have been significantly rarer on Chimera’s shelf than on other top investor shelves. The observable credit mixes of the three shelves appear similar. We ran this analysis with only full-doc loans and from only one state (California), and the rank-ordering of delinquency rates by shelves remains the same. Further to this point, note that the spread at origination of Chimera’s shelf is nearly as high as Flagstar’s. All of this suggests there is something not directly observable about Chimera’s shelf that has generated better credit performance during this stressed period. We caution that differences in servicer reporting of COVID forbearances can distort delinquency data, so we will continue to monitor this performance as our data updates each month.

Figure 8: Chimera Posts Lowest COVID Delinquencies, with Nearly Highest SATO of Top Investor Shelves
Investor DQ60+ rates over time, bucketed by shelf. Includes prime credit, ages 12-60 months.

Chimera Posts Lowest COVID Delinquencies, with Nearly Highest SATO of Top Investor Shelves
Source: CoreLogic, RiskSpan

The Greater Default Risk of Low-Doc Investor Loans Lasts About 10 Years

Low-doc investors default more frequently than full-doc investors, but only during the first roughly 120 months of loan age. Around this age, the default rates converge. For loans seasoned beyond this age, full-doc loans begin to default slightly more frequently than low-doc loans, likely due to a survivorship bias. This suggests that credit investors are wise to require a price discount for new issuance with low-doc collateral. For deals with heavily seasoned collateral, junior-tranche investors may counterintuitively prefer low-doc collateral — certainly if they can earn an extra risk premium for it, as it would seem they are not actually bearing any extra credit risk.

Figure 9: Low-Doc Investor Loans Default More Frequently Than Full-Doc Until Loan Age = 120
Investor default rates over time, bucketed by doc type. Includes prime credit, RMBS 2.0 era, for the past 7yr performance period.

Low-Doc Investor Loans Default More Frequently Than Full-Doc Until Loan Age = 120 Source: CoreLogic, RiskSpan

Summary

  • Investor loans face higher barriers to refinance than owner-occupied, offering RMBS investors the opportunity to earn higher coupons for longer periods.
  • For junior tranche investors, the credit performance of investor loans has been similar to owner-occupied loans during benign economic periods and worse during stressed times.
  • California borrowers respond more quickly to refinance incentives than borrowers from other states; investors will prefer less California collateral.
  • Limited-doc investor loans offer AAA investors a double benefit: slower refinances in the money, extending premium bonds; and faster turnover out of the money, limiting extension risk.
  • Low loan balances are attractive for their slow refinance response – as are non-conforming (high) loan balances above $800K. Traditional prepay models may miss this latter dynamic.
  • For credit investors, Chimera’s delinquency rates have been significantly better during the pandemic than other investor shelves. We will continue to monitor this as different ways of reporting COVID forbearances may confound such comparisons.
  • For credit investors, limited-doc investor loans default at higher rates than full-doc loans for about the first ten years of loan age; after this point the two perform very similarly, with limited-doc loans defaulting at slightly lower rates among these seasoned loans, likely due to survivor biases.

Contact Us

Contact us if you are interested in seeing variations on this theme. Using Edge, we can examine any loan characteristic and generate an S-curve, aging curve, or time series.

Prepayment Spikes in Ida’s Wake – What to Expect

It is, of course, impossible to view the human suffering wrought by Hurricane Ida without being reminded of Hurricane Katrina’s impact 16 years ago. Fortunately, the levees are holding and Ida’s toll appears likely to be less severe. It is nevertheless worth taking a look at what happened to mortgages in the wake of New Orleans’s last major catastrophic weather event as it is reasonable to assume that prepayments could follow a similar pattern (though likely in a more muted way).

Following Katrina, prepayment speeds for pools of mortgages located entirely in Louisiana spiked between November 2005 and June 2006. As the following graph shows, prepayment speeds on Louisiana properties (the black curve) remained elevated relative to properties nationally (the blue curve) until the end of 2006. 

Comparing S-curves of Louisiana loans (the black curve in the chart below) versus all loans (the green curve) during the spike period (Nov. 2005 to Jun. 2006) reveals speeds ranging from 10 to 20 CPR faster across all refinance incentives. The figure below depicts an S-curve for non-spec 100% Louisiana pools and all non-spec pools with a weighted average loan age of 7 to 60 months during the period indicated.

The impact of Katrina on Louisiana prepayments becomes even more apparent when we consider speeds prior to the storm. As the S-curves below show, non-specified 100% Louisiana pools (the black curve) actually paid slightly slower than all non-spec pools between November 2003 and October 2005.

As we pointed out in June, a significant majority of prepayments caused by natural disaster events are likely to be voluntary, as opposed to the result of default as one might expect. This is because mortgages on homes that are fully indemnified against these perils are likely to be prepaid using insurance proceeds. This dynamic is reflected in the charts below, which show elevated voluntary prepayment rates running considerably higher than the delinquency spike in the wake of Katrina. We are able to isolate voluntary prepayment activity by looking at the GSE Loan Level Historical Performance datasets that include detailed credit information. This enables us to confirm that the prepay spike is largely driven by voluntary prepayments. Consequently, recent covid-era policy changes that may reduce the incidence of delinquent loan buyouts from MBS are unlikely to affect the dynamics underlying the prepayment behavior described above.

RiskSpan’s Edge Platform enables users to identify Louisiana-based loans and pools by drilling down into cohort details. The example below returns over $1 billion in Louisiana-only pools and $70 billion in Louisiana loans as of the August 2021 factor month.

Edge also allows users to structure more specified queries to identify the exposure of any portfolio or portfolio subset. Edge, in fact, can be used to examine any loan characteristic to generate S-curves, aging curves, and time series.  Contact us to learn more.

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.

EDGE: Extended Delinquencies in Loan Balance Stories

In June, we highlighted Fannie Mae’s and Freddie Mac’s new “expanded delinquency” states. The Enterprises are now reporting delinquency states from 1 to 24 months to better account for loans that are seriously delinquent and not repurchased under the extended timeframe for repurchase of delinquent loans announced in 2020.

This new data reveals a strong correlation between loan balance and “chronically delinquent” loans. In the graph below, we chart loan balance on the x-axis and 180+Day delinquency on the y-axis, for 2017-18 production 30yr 3.5s through 4.5 “generic” borrowers.[1]

As the graph shows, within a given coupon, loans with larger original balances also tended to have higher “chronic delinquencies.”

EDGE-Orig-Loan-Size

The graph above also illustrates a clear correlation between higher chronic delinquencies and higher coupons. This phenomenon is most likely due to SATO. While each of these queries excluded low-FICO, high-LTV, and NY loans, the 2017-18 30yr 3.5 cohort was mostly at-the-money origination, whereas 4.0s and 4.5s had an average SATO of 30bp and 67bp respectively. The higher SATO indicates a residual credit quality issue. As one would expect, and we demonstrated in our June analysis, lower-credit-quality loans tend also to have higher chronic delinquencies.

The first effect – higher chronic delinquencies among larger loans within a coupon – is more challenging to understand. We posit that this effect is likely due to survivor bias. The large refi wave over the last 18 months has factored-down higher-balance cohorts significantly more than lower-balance cohorts.

EDGE-Factors

Higher-credit-quality borrowers tend to refinance more readily than lower-credit-quality borrowers, and because the larger-loan-balance cohorts have seen higher total prepayments, these same cohorts are left with a larger residue of lower-quality credits. The impact of natural credit migration (which is observed in all cohorts) tends to leave behind a larger proportion of credit-impaired borrowers in faster-paying cohorts versus the slower-paying, lower-loan-balance cohorts.

The higher chronic delinquencies in larger-loan-balance cohorts may ultimately lead to higher buyouts, depending on the resolution path taken. As loan balance decreases, the lower balance cohorts will have reduced risk to these potential buyouts, leaving them better protected to any uptick in involuntary speeds.

Contact us if you are interested in seeing variations on this theme. Using Edge, we can examine any loan characteristic and generate a S-curve, aging curve, or time series.

[1] We filtered for borrowers with LTV<=80, FICO>=700, and ex-NY. We chose 2017-18 production to analyze, to give sufficient time for loans to go chronically delinquent. We see a similar relationship in 2019 production, see RiskSpan for details.

EDGE: Extended Delinquencies in FNMA and FHLMC Loans

In June, the market got its first look at Fannie Mae and Freddie Mac “expanded delinquency” states. The Enterprises are now reporting delinquency states out to 24 months to better account for loans that are seriously delinquent and not repurchased under the extended timeframe for repurchase of delinquent loans announced in 2020. In this short post, we analyze those pipelines and what they could mean for buyouts in certain spec pool stories. 

First, we look at the extended pipeline for some recent non-spec cohorts. The table below summarizes some major 30yr cohorts and their months delinquent. We aggregate the delinquencies that are more than 6 months delinquent[1] for ease of exposition. 

Recent-vintage GSE loans with higher coupons show a higher level of “chronically delinquent” loans, similar to the trends we see in GNMA loans. 

Digging deeper, we filtered for loans with FICO scores below 680. Chronically delinquent loan buckets in this cohort are marginally more prevalent relative to non-spec borrowers. Not unexpectedly, this suggests a credit component to these delinquencies.

Finally, we filtered for loans with high LTVs at origination. The chronically delinquent buckets are lower than the low FICO sector but still present an overhang of potential GSE repurchases in spec pools.

It remains to be seen whether some of these borrowers will be able to resume their original payments —  in which case they can remain in the pool with a forbearance payment due at payoff — or if the loans will be repurchased by the GSEs at 24 months delinquent for modification or other workout. If the higher delinquencies lead to the second outcome, the market could see an uptick in involuntary speeds on some spec pool categories in the next 6-12 months.

Contact us if you are interested in seeing variations on this theme. Using Edge, we can examine any loan characteristic and generate a S-curve, aging curve, or time series.

[1] The individual delinquency states are available for each bucket, contact us for details.

Data & Machine Learning Workshop Series

RiskSpan’s Edge Platform is supported by a dynamic team of professionals who live and breathe mortgage and structured finance data. They know firsthand the challenges this type of data presents and are always experimenting with new approaches for extracting maximum value from it.

In this series of complimentary workshops our team applies machine learning and other innovative techniques to data that asset managers, broker-dealers and mortgage bankers care about.

Machine-Learning-Data-Workshop-Series

Check out our recorded workshops

Measuring and Visualizing Feature Impact & Machine Learning Model Materiality

RiskSpan CIO Suhrud Dagli demonstrates in greater detail how machine learning can be used in input data validations, to measure feature impact, and to visualize how multiple features interact with each other.

Structured Data Extraction from Images Using Google Document AI

RiskSpan Director Steven Sun shares a procedural approach to tackling the difficulties of efficiently extracting structured data from images, scanned documents, and handwritten documents using Google’s latest Document AI Solution.

Pattern Recognition in Time Series Data

Traders and investors rely on time series patterns generated by asset performance to inform and guide their trading and asset allocation decisions. Economists take advantage of analogous patterns in macroeconomic and market data to forecast recessions and other market events. But you need to be able to spot these patterns in order to use them.

Advanced Forecasting Using Hierarchical Models

Traditional statistical models apply a single set of coefficients by pooling a large dataset or for specific cohorts. Hierarchical models learn from feature behavior across dimensions or timeframes. This informative workshop applies hierarchical models to a variety of mortgage and structured finance use cases.

Quality Control with Anomaly Detection (Part I)

Outliers and anomalies refer to various types of occurrences in a time series. Spike of value, shift in level or volatility or a change in seasonal pattern are common examples.  RiskSpan Co-Founder & CIO Suhrud Dagli is joined by Martin Kindler, a market risk practitioner who has spent decades dealing with outliers.

Quality Control with Anomaly Detection (Part 2)

Suhrud Dagli presents Part 2 of this workshop, which dove into mortgage loan QC and introduce coding examples and approaches for avoiding false negatives using open-source Python algorithms in the Anomaly Detection Toolkit (ADTK).

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? 

RS-Tech-Talent

Mortgage DQs by MSA: Non-Agency Performance Chart of the Month

This month we take a closer look at geographical differences in loan performance in the non-agency space. The chart below looks at the 60+ DPD Rate for the 5 Best and Worst performing MSAs (and the overall average). A couple of things to note:

  • The pandemic seems to have simply amplified performance differences that were already apparent pre-covid. The worst performing MSAs were showing mostly above-average delinquency rates before last year’s disruption.
  • Florida was especially hard-hit. Three of the five worst-performing MSAs are in Florida. Not surprisingly, these MSAs rely heavily on the tourism industry.
  • New York jumped from being about average to being one of the worst-performing MSAs in the wake of the pandemic. This is not surprising considering how seriously the city bore the pandemic’s brunt.
  • Tech hubs show strong performance. All our best performers are strong in the Tech industry—Austin’s the new Bay Area, right?
Contact Us

Anomaly Detection and Quality Control

In our most recent workshop on Anomaly Detection and Quality Control (Part I), we discussed how clean market data is an integral part of producing accurate market risk results. As incorrect and inconsistent market data is so prevalent in the industry, it is not surprising that the U.S. spends over $3 trillion on processes to identify and correct market data.

In taking a step back, it is worth noting what drives accurate market risk analytics. Clearly, having accurate portfolio holdings with correct terms and conditions for over-the-counter trades is central to calculating consistent risk measures that are scaled to the market value of the portfolio. The use of well-tested and integrated industry-standard pricing models is another key factor in producing reliable analytics. In comparison to the two categories above, clean, and consistent market data are the largest contributors that could lead to poor market risk analytics. The key driving factor behind detecting and correcting/transforming market data is risk and portfolio managers expectation that risk results are accurate at the start of the business day with no need to perform any time-consuming re-runs during the day to correct issues found. 

Broadly defined, market data is defined as any data that is used as input to the re-valuation models. This includes equity prices, interest rates, credit spreads. FX rates, volatility surfaces, etc.

Market data needs to be:

  • Complete – no true gaps when looking back historically.
  • Accurate
  • Consistent – data must be viewed across other data points to determine its accuracy (e.g., interest rates across tenor buckets, volatilities across volatility surface)

Anomaly types can be broken down into four major categories:

  • Spikes
  • Stale data
  • Missing data
  • Inconsistencies

Here are three example of “bad” market data:

Credit Spreads

The following chart depicts day-over-day changes in credit spreads for the 10-year consumer cyclical time series, returned from an external vendor. The changes indicate a significant spike on 12/3 that caused big swings, up and down, across multiple rating buckets​. Without an adjustment to this data, key risk measures would show significant jumps, up and down, depending on the dollar value of positions on two consecutive days​.

Anomaly Detection

Swaption Volatilities

Market data also includes volatilities, which drive delta and possible hedging. The following chart shows implied swaption volatilities for different maturities of swaptions and their underlying swap​s. The following chart shows implied swaption volatilities for different maturity of swaption and underlying swap​. Note the spikes in 7×10 and 10×10 swaptions. The chart also highlights inconsistencies between different tenors and maturities.

Anomaly-Detection

Equity Implied Volatilities

The 146 and 148 strikes in the table below reflect inconsistent vol data, as often occurs around expiration.

Anomaly-Detection

The detection of market data inconsistencies needs to be an automated process with multiple approaches targeted for specific types of market data. The detection models need to evolve over time as added information is gathered with the goal of reducing false negatives to a manageable level. Once the models detect the anomalies, the next step is to automate the transformation of the market data (e.g., backfill, interpolate, use prior day value). Together with the transformation, transparency must be recorded such that it is known what values were either changed or populated if not available. This should be shared with clients which could lead to alternative transformations or model detection routines.

Detector types typically fall into the following categories:

  • Extreme Studentized Deviate (ESD): finds outliers in a single data series (helpful for extreme cases.)
  • Level Shift: detects change in level by comparing means of two sliding time windows (useful for local outliers.)
  • Local Outliers: detects spikes in near values.
  • Seasonal Detector: detects seasonal patterns and anomalies (used for contract expirations and other events.)
  • Volatility Shift: detects shift of volatility by tracking changes in standard deviation.

On Wednesday, May 19th, we will present a follow-up workshop focusing on:

  • Coding examples
    • Application of outlier detection and pipelines
    • PCA
  • Specific loan use cases
    • Loan performance
    • Entity correction
  • Novelty Detection
    • Anomalies are not always “bad”
    • Market monitoring models

You can register for this complimentary workshop here.

Leveraging ML to Enhance the Model Calibration Process

Last month, we outlined an approach to continuous model monitoring and discussed how practitioners can leverage the results of that monitoring for advanced analytics and enhanced end-user reporting. In this post, we apply this idea to enhanced model calibration.

Continuous model monitoring is a key part of a modern model governance regime. But testing performance as part of the continuous monitoring process has value that extends beyond immediate governance needs. Using machine learning and other advanced analytics, testing results can also be further explored to gain a deeper understanding of model error lurking within sub-spaces of the population.

Below we describe how we leverage automated model back-testing results (using our machine learning platform, Edge Studio) to streamline the calibration process for our own residential mortgage prepayment model.

The Problem:

MBS prepayment models, RiskSpan’s included, often provide a number of tuning knobs to tweak model results. These knobs impact the various components of the S-curve function, including refi sensitivity, turnover lever, elbow shift, and burnout factor.

The knob tuning and calibration process is typically messy and iterative. It usually involves somewhat-subjectively selecting certain sub-populations to calibrate, running back-testing to see where and how the model is off, and then tweaking knobs and rerunning the back-test to see the impacts. The modeler may need to iterate through a series of different knob selections and groupings to figure out which combination best fits the data. This is manually intensive work and can take a lot of time.

As part of our continuous model monitoring process, we had already automated the process of generating back-test results and merging them with actual performance history. But we wanted to explore ways of taking this one step further to help automate the tuning process — rerunning the automated back-testing using all the various permutations of potential knobs, but without all the manual labor.

The solution applies machine learning techniques to run a series of back-tests on MBS pools and automatically solve for the set of tuners that best aligns model outputs with actual results.

We break the problem into two parts:

  1. Find Cohorts: Cluster pools into groups that exhibit similar key pool characteristics and model error (so they would need the same tuners).

TRAINING DATA: Back-testing results for our universe of pools with no model tuning knobs applied

  1. Solve for Tuners: Minimize back-testing error by optimizing knob settings.

TRAINING DATA: Back-testing results for our universe of pools under a variety of permutations of potential tuning knobs (Refi x Turnover)

  1. Tuning knobs validation: Take optimized tuning knobs for each cluster and rerun pools to confirm that the selected permutation in fact returns the lowest model errors.

Part 1: Find Cohorts

We define model error as the ratio of the average modeled SMM to the average actual SMM. We compute this using back-testing results and then use a hierarchical clustering algorithm to cluster the data based on model error across various key pool characteristics.

Hierarchical clustering is a general family of clustering algorithms that build nested clusters by either merging or splitting observations successively. The hierarchy of clusters is represented as a tree (or dendrogram). The root of the tree is the root cluster that contains all samples, while the leaves represent clusters with only one sample. [1]

Agglomerative clustering is an implementation of hierarchical clustering that takes the bottom-up approach (merging approach). Each observation starts in its own cluster, and clusters are then successively merged together. There are multiple linkage criteria that could be chosen from. We have used Ward linkage criteria.

Ward linkage strategy minimizes the sum of squared differences within all clusters. It is a variance-minimizing approach.[2]

Part 2: Solving for Tuners

Here our training data is expanded to be a set of back-test results to include multiple results for each pool under different permutations of tuning knobs.  

Process to Optimize the Tuners for Each Cluster

Training Data: Rerun the back-test with permutations of REFI and TURNOVER tunings, covering all reasonably possible combinations of tuners.

  1. These permutations of tuning results are fed to a multi-output regressor, which trains the machine learning model to understand the interaction between each tuning parameter and the model as a fitting step.
    • Model Error and Pool Features are used as Independent Variables
    • Gradient Tree Boosting/Gradient Boosted Decision Trees (GBDT)* methods are used to find the optimized tuning parameters for each cluster of pools derived from the clustering step
    • Two dependent variables — Refi Tuner and Turnover Tuner – are used
    • Separate models are estimated for each cluster
  2. We solve for the optimal tuning parameters by running the resulting model with a model error ratio of 1 (no error) and the weighted average cluster features.

* Gradient Tree Boosting/Gradient Boosted Decision Trees (GBDT) is a machine learning technique for regression and classification problems, which produces a prediction model in the form of an ensemble of weak prediction models, typically decision trees. When a decision tree is a weak learner, the resulting algorithm is called gradient boosted trees, which usually outperforms random forest. It builds the model in a stage-wise fashion like other boosting methods do, and it generalizes them by allowing optimization of arbitrary differentiable loss function. [3]

*We used scikit-learn’s GBDT implementation to optimize and solve for best Refi and Turnover tuner. [4]

Results

The resultant suggested knobs show promise in improving model fit over our back-test period. Below are the results for two of the clusters using the knobs that suggested by the process. To further expand the results, we plan to cross-validate on out-of-time sample data as it comes in.

Conclusion

These advanced analytics show promise in their ability to help streamline the model calibration and tuning process by removing many of the time-consuming and subjective components from the process altogether. Once a process like this is established for one model, applying it to new populations and time periods becomes more straightforward. This analysis can be further extended in a number of ways. One in particular we’re excited about is the use of ensemble models—or a ‘model of models’ approach. We will continue to tinker with this approach as we calibrate our own models and keep you apprised on what we learn.

Logo

Company

Products

Security & Compliance

Amazon Web Services
Microsoft

Linkedin

SOC2 Type II Certified

Get Started
Log in

Linkedin   

risktech2024