Credit Lending
With the constant (and improving!) changes in the consumer credit landscape, understanding the latest trends is vital for institutions to validate current business strategies or make adjustments to shifts in the marketplace. For example, a recent article in American Banker described how a couple of housing advocates who foretold the housing crisis in 2005 are now promoting a return to subprime lending. Good story lead-in, but does it make sense for “my” business? How do you profile this segment of the market and its recent performance? Are there differences by geography? What other products are attracting this risk segment that could raise concerns for meeting a new mortgage obligation? There is a proliferation of consumer loan and credit information online from various associations and organizations, but in a static format that still makes it challenging to address these types of questions. Fortunately, new web-based solutions are being made available that allow users to access and interrogate consumer trade information 24x7 and keep abreast of constantly changing market conditions. The ability to manipulate and tailor data by geography, VantageScore risk segments and institution type are just a mouse click away. More importantly, these tools allow users to customize the data to meet specific business objectives, so the next subprime lending headline is not just a story, but a real business opportunity based on objective, real-time analysis.
As a scoring manager, this question has always stumped me because there was never a clear answer. It simply meant less than prime – but how much less? What does the term actually mean? How do you quantify something so subjective? Do you assign it a credit score? Which one? There were definitely more questions than answers. But a new proposed ruling from the FDIC could change all that – at least when it comes to large bank pricing assessments. The proposed ruling does a couple of things to bring clarity to the murky waters of the subprime definition. First, it replaces the term “subprime” with “high-risk consumer loans”. Then they go one better: they quantify high-risk as having a 20% probability of default or higher. Finally, something we can calculate! The arbitrary 3-digit credit score that has been used in the past to define the line between prime and subprime has several flaws. First of all, if a subprime loan is defined as having any particular credit score, it has to be for a specific version of a specific model at a specific time. That’s because the default rates associated to any given score is relative to the model used to calculate it. There are hundreds of custom-build and generic scoring models in use by lenders today – does that single score represent the same level of risk to all of them? Absolutely not. And even if all risk models were calibrated exactly the same, just assigning credit risk a number has no real meaning over time. We all know what scores shift, that consumer credit behavior is not the same today as it was just 6 years ago. In 2006, if a score of X represented a 15% likelihood of default, that same score today could represent 20% or more. It is far better to align a definition of risk with its probability of default to begin with! While it only currently applies to the large bank pricing assessments with the FDIC, this proposed ruling is a great step in the right direction. As this new approach catches on, we may see it start to move into other polices and adopted by various organizations as they assess risk throughout the lending cycle.
By: Mike Horrocks This week, several key financial institutions will be submitting their “living wills” to Washington as part of the Dodd-Frank legislation. I have some empathy for how those institutions will feel as they submit these living wills. I don’t think that anyone would say writing a living will is fun. I remember when my wife and I felt compelled to have one in place as we realized that we did not want to have any questions unanswered for our family. For those not familiar with the concept of the living will, I thought I would first look at the more widely known medical description. The Mayo Clinic describes living wills as follows, “Living wills and other advance directives describe your preferences regarding treatment if you\'re faced with a serious accident or illness. These legal documents speak for you when you\'re not able to speak for yourself — for instance, if you\'re in a coma.” Now imagine a bank in a coma. I appreciate the fact that these living wills are taking place, but pulling back my business law books, I seem to recall that one of the benefits of a corporation versus say a sole proprietorship is that the corporation can basically be immortal or even eternal. In fact the Dictionary.com reference calls out that a corporation has “a continuous existence independent of the existences of its members”. So now imagine a bank eternally in a coma. Now, I cannot avoid all of those unexpected risks that will come up in my personal life, like an act of God, that may put me into a coma and invoke my living will, but I can do things voluntarily to make sure that I don’t visit the Emergency Room any time soon. I can exercise, eat right, control my stress and other healthy steps and in fact I meet with a health coach to monitor and track these things. Banks can take those same steps too. They can stay operationally fit, lend right, and monitor the stress in their portfolios. They can have their health plans in place and have a personal trainer to help them stay fit (and maybe even push them to levels of fitness they did not think they could reach). Now imagine a fit, strong bank. So as printers churn, inboxes get filled, and regulators read through thousands of pages of bank living wills, let’s think of the gym coach, or personal trainer that pushed us to improve and think about how we can be healthy and fit and avoid the not so pleasant alternatives of addressing a financial coma.
By: Joel Pruis From a score perspective we have established the high level standards/reporting that will be needed to stay on top of the resulting decisions. But there is a lot of further detail that should be considered and further segmentation that must be developed or maintained. Auto Decisioning A common misperception around auto-decisioning and the use of scorecards is that it is an all or nothing proposition. More specifically, if you use scorecards, you have to make the decision entirely based upon the score. That is simply not the case. I have done consulting after a decisioning strategy based upon this misperception and the results are not pretty. Overall, the highest percentage for auto-decisioning that I have witnessed has been in the 25 – 30% range. The emphasis is on the “segment”. The segments is typically the lower dollar requests, say $50,000 or less, and is not the percentage across the entire application population. This leads into the discussion around the various segments and the decisioning strategy around each segment. One other comment around auto-decisioning. The definition related to this blog is the systematic decision without human intervention. I have heard comments such as “competitors are auto-decisioning up to $1,000,000”. The reality around such comments is that the institution is granting loan authority to an individual to approve an application should it meet the particular financial ratios and other criteria. The human intervention comes from verifying that the information has been captured correctly and that the financial ratios make sense related to the final result. The last statement is the key to the disqualification of “auto-decisioning”. The individual is given the responsibility to ensure data quality and to ensure nothing else is odd or might disqualify the application from approval or declination. Once a human eye is looking at an application, judgment comes into the picture and we introduce the potential for inconsistencies and or extension of time to render the decision. Auto-decisioning is just that “Automatic”. It is a yes/no decision and is based upon objective factors that if met, allow the decision to be made. Other factors, if not included in the decision strategy, are not included. So, my fellow credit professionals, should you hear someone say they are auto-decisioning a high percent of their applications or a high dollar amount for an application, challenge, question and dig deeper. Treat it like the fishing story “I caught a fish THIS BIG”. No financials segment The highest volume of applications and the lowest total dollar production area of any business banking/small business product set. We had discussed the use of financials in the prior blog around application requirements so I will not repeat that discussion here. Our focus will be on the decisioning of these applications. Using score and application characteristics as the primary data source, this segment is the optimal segment for auto-decisioning. Speeds the decision process and provides the greatest amount of consistency in the decisions rendered. Two key areas for this segment are risk premiums and scorecard validations. The risk premium is important as you are going to accept a higher level of losses for the sake of efficiencies in the underwriting/processing of the application. The end result is lower operational costs, relatively higher credit losses but the end yield on this segment meets the required, yet practical, thresholds for return. The one thing that I will repeat from a prior blog is that you may request financials after the initial review but the frequency should be low and should also be monitored. The request of financials should not be the “belt and suspenders” approach. If you know what the financials are likely to show, then don’t request them. They are unnecessary. You are probably right and the collection of the financials will only serve to elongate the response time, frustrate everyone involved in the process and not change the expected results. Financials segment The relatively lower unit volume but the higher dollar volume segment. Likely this segment will have no auto-decisioning as the review of financials typically will mandate the judgmental review. From an operational perspective, these are high dollar and thus the manual review does not push this segment into a losing proposition. From a potential operational lift perspective, the ability to drive a higher volume of applications into auto-decisioning is simply not available as we are talking probably less than 40% (if not fewer) of all applications in this segment. In this segment, the consistency becomes more difficult as the underwriter tends to want to put his/her own approach on the deal. Standardization of the analysis approach (at least initially) is critical for this segment. Consistency in the underwriting and the various criteria allows for greater analysis to determine where issues are developing or where we are realizing the greatest success. My recommended approach is to standardize (via automation in the origination platform) the various calculations in a manner that will generate the most conservative approach. Bluntly put, my approach was to attempt to make the deal as ugly as possible and if it still passed the various criteria, no additional work was needed nor was there any need for detailed explanation around how I justified the deal/request. Only if it did not meet the criteria using the most conservative approach would I need to do any work and only if it was truly going to make a difference. Basic characteristics in this segment include – business cash flow, personal debt to income, global cash flow and leverage. Others may be added but on a case by case basis. What about the score? If I am doing so much judgmental underwriting, why calculate the score in this segment? In a nutshell, to act as the risk rating methodology for the portfolio approach. Even with the judgmental approach, we do not want to fall into the trap thinking we are going to be able to adequately monitor this segment in a proactive fashion to justify the risk rating at any point in time after the loan is booked. We have been focusing on the origination process in this blog series but I need to point out that since we are not going to be doing a significant amount of financial statement monitoring in the small business segment, we need to begin to move away from the 1 – 8 (or 9 or 10 or whatever) risk rating method for the small business segment. We cannot be granular enough with this rating system nor can we constantly stay on top of what may be changing risk levels related to the individual clients. But I am going to save the portfolio management area for a future blog. Regardless of the segment, please keep in mind that we need to be able to access the full detail of the information that is being captured during the origination process along with the subsequent payment performance. As you are capturing the data, keep in mind, the abilities to Access this data for purposes of analysis Connect the data from origination to the payment performance data to effectively validate the scorecard and my underwriting/decisioning strategies Dive into the details to find the root cause of the performance problem or success The topic of decisioning strategies is broad so please let me know if you have any specific topics that you would like addressed or questions that we might be able to post for responses from the industry.
Recently we released a white paper that emphasizes the need for better, more granular indicators of local home-market conditions and borrower home equity, with a very interesting new finding on leading indicators in local-area credit statistics. Click here to download the white paper Home-equity indicators with new credit data methods for improved mortgage risk analytics Experian white paper, April 2012 In the run-up to the U.S. housing downturn and financial crisis, perhaps the greatest single risk-management shortfall was poorly predicted home prices and borrower home equity. This paper describes new improvements in housing market indicators derived from local-area credit and real-estate information. True housing markets are very local, and until recently, local real-estate data have not been systematically available and interpreted for broad use in modeling and analytics. Local-area credit data, similarly, is relatively new, and its potential for new indicators of housing market conditions is studied here in Experian’s Premier Aggregated Credit Statistics.SM Several examples provide insights into home-equity indicators for improved mortgage models, predictions, strategies, and combined LTV measurement. The paper finds that for existing mortgages evaluated with current combined LTV and borrower credit score, local-area credit statistics are an even stronger add-on default predictor than borrower credit attributes. Click here to download the white paper Authors: John Straka and Chuck Robida, Experian Michael Sklarz, Collateral Analytics
Previously, we looked at the various ways a dual score strategy could help you focus in on an appropriate lending population. Find your mail-to population with a prospecting score on top of a risk score; locate the riskiest of all consumers by layering a bankruptcy score with your risk model. But other than multiple scores, what other tools can be used to improve credit scoring effectiveness? Credit attributes add additional layers of insight from a risk perspective. Not everyone who scores an 850 represent the same level of risk once you start interrogating their broader profile. How much total debt are they carrying? What is the nature of it - is it mortgage or mostly revolving? A credit score may not fully articulate a consumer as high risk, but if their debt obligations are high, they may represent a very different type of risk than from another consumer with the same 850 score. Think of attribute overlays in terms of tuning the final score valuation of an individual consumer by making the credit profile more transparent, allowing a lender to see more than just the risk odds associated with the initial score. Attributes can also help you refine offers. A consumer may be right for you in terms of risk, but are you right for them? If they have 4 credit cards with $20K limits each, they’re likely going to toss your $5K card offer in the trash. Attributes can tell us these things, and more. For example, while a risk score can tell us what the risk of a consumer is within a set window, certain credit attributes can tell us something about the stability of that consumer to remain within that risk band. Recent trends in score migration – the change in a level of creditworthiness of a consumer subsequent to generation of a current credit score – can undermine the most conservative of risk management policies. At the height of the recession, VantageScore LLC studied the migration of scores across all risk bands and was able to identify certain financial management behaviors found within their credit files. These behaviors (signaling, credit footprint, and utility) assess the consumer’s likelihood of improving, significantly deteriorating, or maintaining a stable score over the next 12 months. Knowing which subgroup of your low-risk population is deteriorating, or which high risk groups are improving, can help you make better decision today.
Up to this point, I’ve been writing about loan originations and the prospects and challenges facing bankcard, auto and real estate lending this year. While things are off to a good start, I’ll use my next few posts to discuss the other side of the loan equation: performance. If there’s one thing we learned during the post-recession era is that growth can have consequences if not managed properly. Obviously real estate is the poster child for this phenomenon, but bankcards also realized significant and costly performance deterioration following the rapid growth generated by relaxed lending standards. Today, bankcard portfolios are in expansion mode once again, but with delinquency rates at their lowest point in years. In fact, loan performance has improved nearly 50% in the past three years through a combination of tighter lending requirements and consumers’ self-imposed deleveraging. Lessons learned from issuers and consumers have created a unique climate in which growth is now balanced with performance. Even areas with greater signs of payment stress have realized significant improvements. For example, the South Atlantic region’s 4.2% 30+ DPD performance is 11% higher than the national average, but down 27% from a year ago. Localized economic factors definitely play a part in performance, but the region’s higher than average origination growth from a broader range of VantageScore consumers could also explain some of the delinquency stress here. And that is the challenge going forward: maintaining bankcard’s recent growth while keeping performance in check. As the economy and consumer confidence improves, this balancing act will become more difficult as issuers will want to meet the consumer’s appetite for spending and credit. Increased volume and utilization is always good for business, but it won’t be until the performance of these loans materializes that we’ll know whether it was worth it.
Last month, I wrote about seeking ways to ensure growth without increasing risk. This month, I’ll present a few approaches that use multiple scores to give a more complete view into a consumer’s true profile. Let’s start with bankruptcy scores. You use a risk score to capture traditional risk, but bankruptcy behavior is significantly different from a consumer profile perspective. We’ve seen a tremendous amount of bankruptcy activity in the market. Despite the fact that filings were slightly lower than 2010 volume, bankruptcies remain a serious threat with over 1.3 million consumer filings in 2011; a number that is projected for 2012. Factoring in a bankruptcy score over a traditional risk score, allows better visibility into consumers who may be “balance loading”, but not necessarily going delinquent, on their accounts. By looking at both aspects of risk, layering scores can identify consumers who may look good from a traditional credit score, but are poised to file bankruptcy. This way, a lender can keep their approval rates up and lower risk of overall dollar losses. Layering scores can be used in other areas of the customer life cycle as well. For example, as new lending starts to heat up in markets like Auto and Bankcard, adding a next generation response score to a risk score in your prospecting campaigns, can translate into a very clear definition of the population you want to target. By combining a prospecting score with a risk score to find credit worthy consumers who are most likely to open, you help mitigate the traditional inverse relationship between open rates and credit worthiness. Target the population that is worth your precious prospecting resources. Next time, we’ll look at other analytics that help complete our view of consumer risk. In the meantime, let me know what scoring topics are on your mind.
By: Mike Horrocks Henry Ford is credited to have said “Coming together is a beginning. Keeping together is progress. Working together is success.” This is so true with risk management, as you may consider bringing in different business units, policies, etc., into a culture of enterprise risk management. Institutions that understand the concept of strength from unity are able to minimize risks at all levels, and not be exposed in unfamiliar areas. So how can this apply in your organization? Is your risk management process united across all different business lines or are there potential chinks in your armor? Are you using different guidelines to manage risk as it comes in the door, versus how you are looking at it once it is part of the portfolio, or are they closely unified in purpose? Now don’t get me wrong, I am not saying that blind cohesion is right for every risk management issue, but getting efficiencies and consistencies can do wonders for your overall risk management process. Here are some great questions to help you evaluate where you are: Is there a well-understood risk management approach in place across the institution? How confident are you that risk management is a core competence of your institution? Does risk management run through the veins of the institution, or is it regarded as the domain of auditors and compliance? A review of these questions may bring you closer to being one in purpose when it comes to your risk management processes. And while that oneness may not bring you Zen-like inner peace, it will bring your portfolio managers at least a little less stress.
By: Joel Pruis Some of you may be thinking finally we get to the meat of the matter. Yes the decision strategies are extremely important when we talk about small business/business banking. Just remember how we got to here though, we had to first define: Who are we going to pursue in this market segment? How are we going to pursue this market segment - part 1 & part 2? What are we going to require of the applicants to request the funds? Without the above, we can create all the decision strategies we want but their ultimate effectiveness will be severely limited as they will not have a foundation based upon a successful execution. First we are going to lay the foundation for how we are going to create the decision strategy. The next blog post (yes, there is one more!) will get into some more specifics. With that said, it is still important that we go through the basics of establishing the decision strategy. These are not the same as investments. Decision strategies based upon scorecards We will not post the same disclosure as do the financial reporting of public corporations or investment solicitations. This is the standard disclosure of “past performance is not an indication of future results”. On the contrary, for scorecards, past performance is an indication of future results. Scorecards are saying that if all conditions remain the same, future results should follow past performance. This is the key. We need to fully understand what the expected results are to be for the portfolio originated using the scorecard. Therefore we need to understand the population of applications used to develop the scorecards, basically the information that we had available to generate the scorecard. This will tie directly with the information that we required of the applications to be submitted. As we understand the type of applications that we are taking from our client base we can start to understand some expected results. By analyzing what we have processed in the past we can start to build about model for the expected results going forward. Learn from the past and try not to repeat the mistakes we made. First we take a look at what we did approve and analyze the resulting performance of the portfolio. It is important to remember that we are not to be looking for the ultimate crystal ball rather a model that can work well to predict performance over the next 12 to 18 months. Those delinquencies and losses that take place 24, 36, 48 months later should not and cannot be tied back to the information that was available at the time we originated the credit. We will talk about how to refresh the score and risk assessment in a later blog on portfolio management. As we see what was approved and demonstrated acceptable performance we can now look back at those applications we processed and see if any applications that fit the acceptable profile were actually declined. If so, what were the reasons for the declinations? Do these reasons conflict with our findings based upon portfolio performance? If so, we may have found some additional volume of acceptable loans. I say \"may\" because statistics by themselves do not tell the whole story, so be cautious of blindly following the statistical data. My statistics professor in college drilled into us the principle of \"correlation does not mean causation\". Remember that the next time a study featured on the news. The correlation may be interesting but it does not necessarily mean that those factors \"caused\" the result. Just as important, challenge the results but don\'t use outliers to disprove here results or the effectiveness of the models. Once we have created the model and applied it to our typical application population we can now come up with some key metrics that we need to manage our decision strategies: Expected score distributions of the applications Expected approval percentage Expected override percentage Expected performance over the next 12-18 months Expected score distributions We build the models based upon what we expect to be the population of applications we process going forward. While we may target market certain segments we cannot control the walk-in traffic, the referral volume or the businesses that will ultimately respond to our marketing efforts. Therefore we consider the normal application distribution and its characteristics such as 1) score; 2) industry; 3) length of time in business; 4) sales size; etc. The importance of understanding and measuring the application/score distributions is demonstrated in the next few items. Expected approval percentages First we need to consider the approval percentages as an indication of what percent of the business market to which we are extending credit. Assuming we have a good representative sample of the business population in the applications we are processing we need to determine what percentile of businesses will be our targeted market. Did our analysis show that we can accept the top 40%? 50%? Whatever the percentage, it is important that we continue to monitor our approval percentage to determine if we are starting to get too conservative or too liberal in our decisioning. I typically counsel my client that “just because your approval percentage is going up is not necessarily an improvement!” By itself an increase in approval percentage is not good. I\'m not saying that it is bad just that when it goes up (or down!) you need to explain why. Was there a targeted marketing effort? Did you run into a short term lucky streak? OR is it time to reassess the decision model and tighten up a bit? Think about what happens in an economic expansion. More businesses are surviving (note I said surviving not succeeding). Are more businesses meeting your minimum criteria? Has the overall population shifted up? If more businesses are qualifying but there has been no change in the industries targeted, we may need to increase our thresholds to maintain our targeted 50% of the market. Just because they met the standard criteria in the expansion does not mean they will survive in a recession. \"But Joel, the recession might be more than 18 months away so we have a good client for at least 18 months, don\'t we?\". I agree but we have to remember that we built the model assuming all things remain constant. Therefore if we are confident that the expansion will continue at the same pace infinitum, then go ahead and live with the increased approval percentage. I will challenge you that it is those applicants that \"squeaked by\" during the expansion that will be the largest portion of the losses when the recession comes. I will also look to investigate the approval percentages when they go down. Yes you can make the same claim that the scorecard is saying that the risk is too great over the next 12-18 months but again I will challenge that if we continue to provide credit to the top 40-50% of all businesses we are likely doing business with those clients that will survive and succeed when the expansion returns. Again, do the analysis of “why” the approval percentage declined/dropped. Expected override percentage While the approval percentage may fluctuate or stay the same, another area to be reviewed is that of the override. Overrides can be score overrides or a decision override. Score override would be contradicting the decision that was recommended based upon the score and/or overall decision strategy. Decision override would be when the market/field has approval authority and overturns the decision made by the central underwriting group. Consequently you can have a score override, a decision override or both. Overrides can be an explanation for the change in approval percentages. While we anticipate a certain degree of overrides (say around 5%), should the overrides become too significant we start to lose control of the expected outcomes of the portfolio performance. As such we need to determine why the overrides have increase (or potentially decrease) and the overrides impact on the approval percentage. We will address some specifics around override management in a later blog. Suffice to say, overrides will always be present but we need to keep the amount of overrides within tolerances to be sure we can accurate assess future performance. Expected performance over next 12-18 months The measure of expected performance is at minimum the expected probability/propensity of repayment. This may be labeled as the bad rate or the probability of default (PD). In a nutshell it is the probability that the credit facility will be a certain level of delinquency over the next 12-18 months. What the base level expected performance based upon score is not the expected “loss” on the account. That is a combination of the probability of default combined with the expected loss given event of default. For the purpose of this post we are talking about the probability of default and not the loss given event of default. For reinforcement we are simply talking about the percentage of accounts that go 30 or 60 or 90 days past due during the 12 – 18 months after origination. So bottom line, if we maintain a score distribution of the applications processed by the financial institution, maintain the approval percentage as well as the override percentages we should be able to accurately assess the future performance of the newly originated portfolio. Coming up next… A more tactical discussion of the decision strategy
In my last two posts on bankcard and auto originations, I provided evidence as to why lenders have reason to feel optimistic about their growth prospects in 2012. With real estate lending however, the recovery, or lack thereof looks like it may continue to struggle throughout the year. At first glance, it would appear that the stars have aligned for a real estate turnaround. Interest rates are at or near all-time lows, housing prices are at post-bubble lows and people are going back to work with the unemployment rate at a 3-year low just above 8%. However, mortgage originations and HELOC limits were at $327B and $20B for Q3 2011, respectively. Admittedly not all-time quarterly lows, but well off levels of just a couple years ago. And according to the Mortgage Bankers Association, 65% of the mortgage volume was from refinance activity. So why the lull in real estate originations? Ironically, the same reasons I just mentioned that should drive a recovery. Low interest rates – That is, for those that qualify. The most creditworthy, VantageScore A and B consumers made up nearly 77% of the $327B mortgage volume and 87% of the $20B HELOC volume in Q3 2011. While continuing to clean up their portfolios, lenders are adjusting their risk exposure accordingly. Housing prices at multi-year lows - According to the S&P Case Shiller index, housing prices were 4% lower at the end of 2011 when compared to the end of 2010 and at the lowest level since the real estate bubble. Previous to this report, many thought housing prices had stabilized, but the excess inventory of distressed properties continues to drive down prices, keeping potential buyers on the sidelines. Unemployment rate at 3-year low – Sure, 8.3% sounds good now when you consider we were near 10% throughout 2010. But this is a far cry from the 4-5% rate we experienced just five years ago. Many consumers continue to struggle, affecting their ability to make good on their debt obligations, including their mortgage (see “Housing prices at multi-year lows” above), in turn affecting their credit status (see “Low interest rates” above)… you get the picture. Ironic or not, the good news is that these forces will be the same ones to drive the turnaround in real estate originations. Interest rates are projected to remain low for the foreseeable future, foreclosures and distressed inventory will eventually clear out and the unemployment rate is headed in the right direction. The only missing ingredient to make these variables transform from the hurdle to the growth factor is time.
If you attended any of our past credit trends Webinars, you’ve heard me mention time and again how auto originations have been a standout during these times when overall consumer lending has been a challenge. In fact, total originated auto volumes topped $100B in the third quarter of 2011, a level not seen since mid-2008. But is this growth sustainable? Since bottoming at the start of 2009, originations have been on a tear for nearly three straight years. Given that, you might think that auto origination’s best days are behind it. But these three key factors indicate originations may still have room to run: 1. The economy Just as it was a factor in declining auto originations during the recession, the economy will drive continued increases in auto sales. If originations were growing during the challenges of the past couple of years, the expected improvements in the economy in 2012 will surely spur new auto originations. 2. Current cars are old A recent study by Experian Automotive showed that today’s automobiles on the road have hit an all-time high of 10.6 years of age. Obviously a result of the recent recession, consumers owning older cars will result in pent up demand for newer and more reliable ones. 3. Auto lending is more diversified than ever I’m talking diversification in a couple of ways: Auto lending has always catered to a broader credit risk range than other products. In recent years, lenders have experimented with moving even further into the subprime space. For example, VantageScore D consumers now represent 24.4% of all originations vs. 21.2% at the start of 2009. There is a greater selection of lenders that cater to the auto space. With additional players like Captives, Credit Unions and even smaller Finance companies competing for new business, consumers have several options to secure a competitively-priced auto loan. With all three variables in motion, auto originations definitely have a formula for continued growth going forward. Come find out if auto originations do in fact continue to grow in 2012 by signing up for our upcoming Experian-Oliver Wyman credit trends Webinar.
Part II: Where are Models Most Needed Now in Mortgages? (Click here if you missed Part I of this post.) By: John Straka A first important question should always be are all of your models, model uses, and model testing strategies, and your non-model processes, sound and optimal for your business? But in today’s environment, two areas in mortgage stand out where better models and decision systems are most needed now: mortgage servicing and loan-quality assurance. I will discuss loan-quality assurance in a future installment. Mortgage servicing and loss mitigation are clearly one area where better models and new decision analytics continue to have a seemingly great potential today to add significant new value. At the risk of oversimplifying, it is possible that a number of the difficulties and frustrations of mortgage servicers (and regulators) and borrowers in recent years may have been lessened through more efficient automated decision tools and optimization strategies. And because these problems will continue to persist for quite some time, it is certainly not too late to envision and move now towards an improved future state of mortgage servicing, or to continue to advance your existing new strategic direction by adding to enhancements already underway. Much has been written about the difficulties faced by many mortgage servicers who have been overwhelmed by the demands of many more delinquent and defaulted borrowers and very extensive, evolving government involvements in new programs, performance incentives and standards. A strategic question on the minds of many executives and others in the industry today seems to be, where is all of this going? Is there a generally viable strategic direction for mortgage servicers that can help them to emerge from their current issues—perhaps similar to the improved data, standards, modeling, and technologies that allowed the mortgage industry in the 1990s to emerge overall quite successfully from the problems of the late 1980s and early 90s? To review briefly, mortgage industry problems of the early 1990s were less severe, of course—but really not dissimilar to the current environment. There had been a major home-price correction in California, in New England, and in a number of large metro areas elsewhere. A “low doc” mortgage era (and other issues) had left Citicorp nearly insolvent, for example, and caused other significant losses on top of the losses generated by the home prices. A major source of most mortgage funding, the Savings & Loan industry, had largely collapsed, with losses having to be resolved by a special government agency. Statistical mortgage credit scoring and automated underwriting resulted from the improved data, standards, modeling, and technologies that allowed the mortgage industry to recover in the 1990s, allowing mortgages to catch up with the previously established use of this decision technology in cards, autos, etc., thus benefiting the mortgage industry with reduced costs and significant gains in efficiency and risk management. An important question today is, is there a similar “renaissance,” so to speak, now in the offing or at hand for mortgage servicers? Despite all of the still ongoing problems? Let me offer here a very simple analogy—with a disclaimer that this is only a basic starting viewpoint, an oversimplification, recognizing that mortgage servicing and loss mitigation is extraordinarily complex in its details, and often seems only to grow more complex by the day (with added constraints and uncertainties piling on). The simple analogy is this: consider your loan-level Net Present Value (NPV) or other key objective of loan-level decisions in servicing and loss mitigation to be analogous to the statistically based mortgage default “Score” of automated underwriting for originations in the 1990s. Viewed in this way, a simple question stemming from the figure below is: can you reduce costs and satisfy borrowers and performance standards better by automating and focusing your servicing representatives more, or primarily, on the “Refer” group of borrowers? A corollary question is can more automated model-based decision engines confidently reduce the costs and achieve added insights and efficiencies in servicing the lowest and highest NPV delinquent borrowers and the Refer range? Another corollary question is, are new government-driven performance standards helpful or hindering (or even preventing) particular moves toward this type of objective. Is this a generally viable strategic direction for the future (or even the present) of mortgage servicing? Is it your direction today? What is your vision for the future of your quality mortgage servicing?
By: Joel Pruis One might consider this topic redundant to the last submission around application requirements and that assessment would be partially true. As such we are not going to go over the data that has already been collected in the application such as the demographic information of the applicant and guarantors or the business financial information or personal financial information. That discussion like Elvis has “left the building”. Rather, we will discuss the use of additional data to support the underwriting/decisioning process - namely: Personal/Consumer credit data Business data Scorecards Fraud data Let’s get a given out in the open. Personal credit data has a high correlation to the payment performance of a small business. The smaller the business the higher the correlation. “Your honor, counsel requests the above be stipulated in the court records.” “So stipulated for the record.” “Thank you, your honor.” With that put to rest (remember you can always comment on the blog if you have any questions or want to comment on any of the content). The real debate in small business lending revolves around the use of business data. Depth and availability of business data There are some challenges with the gathering and dissemination of business data for use in decisioning - mainly around the history of the data for the individual entity. More specifically, while a consumer is a single entity and for the vast majority of consumers, one does not bankrupt one entity and then start a new person to refresh their credit history. No, that is actually bankruptcy and the bankruptcy stays with the individual. Businesses, however, can and in fact do close one entity and start up another. Restaurants and general contractors come to mind as two examples of individuals who will start up a business, go bankrupt and then start another business under a new entity repeating the cycle multiple times. While this scenario is a challenge, one cannot refute the need to know how both the individual consumer as well as the individual business is handling its obligations whether they are credit cards, auto loans or trade payables. I once worked for a bank president in a small community bank who challenged me with the following mantra, “It’s not what you know that you don’t know that can hurt you, it is what you think you know but really don’t that hurts you the most.” I will admit that it took me a while to digest that statement when I first heard it. Once fully digested the statement was quite insightful. How many times do we think we know something when we really don’t? How many times do we act on an assumed understanding but find that our understanding was flawed? How sound was our decision when we had the flawed understanding? The same holds true as it relates to the use (or lack thereof) of business information. We assume that we don’t need business information because it will not tell us much as it relates to our underwriting. How can the business data be relevant to our underwriting when we know that the business performance is highly correlated to the performance of the owner? Let’s look at a study done a couple of years ago by the Business Information group at Experian. The data comes from a whitepaper titled “Predicting Risk: the relationship between business and consumer scores” and was published in 2008. The purpose of the study was to determine which goes bad first, the business or the owner. At a high level the data shows the following: If you\'re interested, you can download the full study here. So while a majority of time and without any additional segmentation, the business will show signs of stress before the owner. If we look at the data using length of time in business we see some additional insights. Figure: Distribution of businesses by years in business Interesting distinction is that based upon the age of the business we will see the owner going bad before the business if the business age is 5 years or less. Once we get beyond the 5 year point the “first bad” moves to the business. In either case, there is no clear case to be made to exclude one data source in favor of the other to predict risk in a small business origination process. While we can look at see that there is an overall majority where the business goes bad first or that if we have a young small business the owner will more likely go bad first, in either case, there is still a significant population where the inverse is true. Bottom line, gathering both the business and the consumer data allows the financial institution to make a better and more informed decision. In other words, it prevents us from the damage caused by “thinking we know something when we really don’t”. Coming up next month – Decisioning Strategies.
Part I: Types and Complexity of Models, and Unobservable or Omitted Variables or Relationships By: John Straka Since the financial crisis, it’s not unusual to read articles here and there about the “failure of models.” For example, a recent piece in Scientific American critiqued financial model “calibration,” proclaiming in its title, Why Economic Models are Always Wrong. In the mortgage business, for example, it is important to understand where models have continued to work, as well as where they failed, and what this all means for the future of your servicing and origination business. I also see examples of loose understanding about best practices in relation to the shortcomings of models that do work, and also about the comparative strengths and weaknesses of alternative judgmental decision processes. With their automation efficiencies, consistency, valuable added insights, and testability for reliability and robustness, statistical business models driven by extensive and growing data remain all around us today, and they are continuing to expand. So regardless of your views on the values and uses of models, it is important to have a clear view and sound strategies in model usage. A Categorization: Ten Types of Models Business models used by financial institutions can be placed in more than ten categories, of course, but here are ten prominent general types of models: Statistical credit scoring models (typically for default) Consumer- or borrower-response models Consumer- or borrower-characteristic prediction models Loss given default (LGD) and Exposure at default (EAD) models Optimization tools (these are not models, per se, but mathematical algorithms that often use inputs from models) Loss forecasting and simulation models and Value-at-risk (VAR) models Valuation, option pricing, and risk-based pricing models Profitability forecasting and enterprise-cash-flow projection models Macroeconomic forecasting models Financial-risk models that model complex financial instruments and interactions Types 8, 9 and 10, for example, are often built up from multiple component models, and for this reason and others, these model categories are not mutually exclusive. Types 1 through 3, for example, can also be built from individual-level data (typical) or group-level data. No categorical type listing of models is perfect, and this listing is also not intended to be completely exhaustive. The Strain of Complexity (or Model Ambition) The principle of Occam’s razor in model building, roughly translated, parallels the business dictum to “keep it simple, stupid.” Indeed, the general ordering of model types 1 through 10 above (you can quibble on the details) tends to correspond to growing complexity, or growing model ambition. Model types 1 and 2 typically forecast a rank-ordering, for example, rather than also forecasting a level. Credit scores and credit scoring typically seek to rank-order consumers in their default, loss, or other likelihoods, without attempting to project the actual level of default rates, for example, across the score distribution. Scoring models that add the dimension of level prediction increase this layer of complexity. In addition, model types 1 through 3 are generally unconditional predictors. They make no attempt to add the dimension of predicting the time path of the dependent variable. Predicting not just a consumer’s relative likelihood of an event over a future time period as a whole, for example, but also the event’s frequency level and time path of this level each year, quarter, or month, is a more complex and ambitious modeling endeavor. (This problem is generally approached through continuous or discrete hazard models.) While generalizations can be hazardous (exceptions can typically be found), it is generally true that, in the events leading up to and surrounding the financial crisis, greater model complexity and ambition was correlated with greater model failure. For example, at what is perhaps an extreme, Coval, Jurek, and Stafford (2009) have demonstrated how, for model type 10, even slight unexpected changes in default probabilities and correlations had a substantial impact on the expected payoffs and ratings of typical collateralized debt obligations (CDOs) with subprime residential mortgage-backed securities as their underlying assets. Nonlinear relationships in complex systems can generate extreme unreliability of system predictions. To a lesser but still significant degree, the mortgage- or housing-related models included or embedded in types 6 through 10 were heavily dependent on home-price projections and risk simulation, which caused significant “expected”-model failures after 2006. Home-price declines in 2007-2009 reached what had previously only been simulated as extreme and very unlikely stress paths. Despite this clear problem, given the inescapable large impact of home prices on any mortgage model or decision system (of any kind), it is generally acceptable to separate the failure of the home-price projection from any failure of the relative default and other model relationships built around the possible home-price paths. In other words, if a model of type 8, for example, predicted the actual profitability and enterprise cash flow quite well given the actual extreme path of home prices, then this model can be reasonably regarded as not having failed as a model per se, despite the clear, but inescapable reliance of the model’s level projections on the uncertain home-price outcomes. Models of type 1, statistical credit scoring models, generally continued to work well or reasonably well both in the years preceding and during the home-price meltdown and financial crisis. This is very largely due to these models’ relatively modest objective of simply rank-ordering risks, in general. To be sure, scoring models in mortgage, and more generally, were strongly impacted by the home price declines and unusual events of the bubble and subsequent recession, with deteriorated strength in risk separation. This can be seen, for example, in the recent Vantage Score stress-test study, VantageScore 2.0 Stress Testing, which shows the lowest risk separation ability in the states with the worst home-price and unemployment outcomes (CA, AZ, FL, NV, MI). But these kinds of significant but comparatively modest magnitudes of deterioration were neither debilitating nor permanent for these models. In short, even in mortgage, scoring models generally held up pretty well, even through the crisis—not perfectly, but comparatively better than the more complex level-, system-, and path-prediction models. (see footnote 1) Scoring models have also relied more exclusively on microeconomic behavioral stabilities, rather than including macroeconomic risk modeling. Fortunately the microeconomic behavioral patterns have generally been much more stable. Weak-credit borrowers, for example, have long tended to default at significantly higher rates than strong credit borrowers—they did so preceding, and right through, the financial crisis, even as overall default levels changed dramatically; and they continue to do so today, in both strong and weak housing markets. (see footnote 2) As a general rule overall, the more complex and ambitious the model, the more complex are the many questions that have to be asked concerning what could go wrong in model risks. But relative complexity is certainly not the only type of model risk. Sometimes relative simplicity, otherwise typically desirable, can go in a wrong direction. Unobservable or Omitted Variables or Relationships No model can be perfect, for many reasons. Important determining variables may be unmeasured or unknown. Similarly, important parameters and relationships may differ significantly across different types of populations, and different time periods. How many models have been routinely “stress tested” on their robustness in handling different types of borrower populations (where unobserved variables tend to lurk) or different shifts in the mix of borrower sub-populations? This issue is more or less relevant depending on the business and statistical problem at hand, but overall, modeling practice has tended more often than not to neglect robustness testing (i.e., tests of validity and model power beyond validation samples). Several related examples from the last decade appeared in models that were used to help evaluate subprime loans. These models used generic credit scores together with LTV, and perhaps a few other variables (or not), to predict subprime mortgage default risks in the years preceding the market meltdown. This was a hazardous extension of relatively simple model structures that worked better for prime mortgages (but had also previously been extended there). Because, for example, the large majority of subprime borrowers had weak credit records, generic credit scores did not help nearly as much to separate risk. Detailed credit attributes, for example, were needed to help better predict the default risks in subprime. Many pre-crisis subprime models of this kind were thus simplified but overly so, as they began with important omitted variables. This was not the only omitted-variables problem in this case, and not the only problem. Other observable mortgage risk factors were oddly absent in some models. Unobserved credit risk factors also tend to be correlated with observed risk factors, creating greater volatility and unexplained levels of higher risk in observed higher-credit-risk populations. Traditional subprime mortgages also focused mainly on poor-credit borrowers who needed cashout refinancing for debt consolidation or some other purpose. Such borrowers, in shaky financial condition, were more vulnerable to economic shocks, but a debt consolidating cashout mortgage could put them in a better position, with lower total monthly debt payments that were tax deductible. So far, so good—but an omitted capacity-risk variable was the number of previous cashout refinancings done (which loan brokers were incented to “churn”). The housing bubble allowed weak-capacity borrowers to sustain themselves through more extracted home equity, until the music stopped. Rate and fee structures of many subprime loans further heightened capacity risks. A significant population shift also occurred when subprime mortgage lenders significantly raised their allowed LTVs and added many more shaky purchase-money borrowers last decade; previously targeted affordable-housing programs from the banks and conforming-loan space had instead generally required stronger credit histories and capacity. Significant shifts like this in any modeled population require very extensive model robustness testing and scrutiny. But instead, projected subprime-pool losses from the major purchasers of subprime loans, and the ratings agencies, went down in the years just prior to the home-price meltdown, not up (to levels well below those seen in widely available private-label subprime pool losses from 1990’s loans). Rules and Tradition in Lieu of Sound Modeling Interestingly, however, these errant subprime models were not models that came into use in lender underwriting and automated underwriting systems for subprime—the front-end suppliers of new loans for private-label subprime mortgage-backed securities. Unlike the conforming-loan space, where automated underwriting using statistical mortgage credit scoring models grew dramatically in the 1990s, underwriting in subprime, including automated underwriting, remained largely based on traditional rules. These rules were not bad at rank-ordering the default risks, as traditional classifications of subprime A-, B, C and D loans showed. However, the rules did not adapt well to changing borrower populations and growing home-price risks either. Generic credit scores improved for most subprime borrowers last decade as they were buoyed by the general housing boom and economic growth. As a result, subprime-lender-rated C and D loans largely disappeared and the A- risk classifications grew substantially. Moreover, in those few cases where statistical credit scoring models were estimated on subprime loans, they identified and separated the risks within subprime much better than the traditional underwriting rules. (I authored an invited article early last decade, which included a graph, p. 222, that demonstrated this, Journal of Housing Research.) But statistical credit scoring models were scarcely or never used in most subprime mortgage lending. In Part II, I’ll discuss where models are most needed now in mortgages. Footnotes: [1] While credit scoring models performed better than most others, modelers can certainly do more to improve and learn from the performance declines at the height of the home-price meltdown. Various approaches have been undertaken to seek such improvements. [2] Even strategic mortgage defaults, while comprising a relatively larger share of strong-credit borrower defaults, have not significantly changed the traditional rank-ordering, as strategic defaults occur across the credit spectrum (weaker credit histories include borrowers with high income and assets).
Learn More Image
