Automated Valuation Metrics
Earlier this year, Lee Kennedy appeared with Matthew Blake on the HousingWire Daily podcast, Houses in Motion:
They covered a number of topics in valuations, from iBuying to AVMs, including:
Testing an AVM’s accuracy can actually be quite tricky. You might think that you simply compare an AVM valuation to a corresponding actual sales price – technically a fair sale on the open market – but that’s just the beginning. Here’s why it’s hard:
Here’s a secret about that third part: some of the AVM builders are also the same companies that are the premier providers of real estate data, including MLS data. What if the models are using MLS data listing price feeds to “anchor” their models based on the listing price of a home? If they are the source of the data, how can you test them before they get the data? We now know how.
We have spent years developing and implementing a solution because we wanted to level the playing field for every AVM builder and model. We ask each AVM to value every home in America each month. They each provide +/-110 million AVM valuations each month. There are over 25 different commercially available AVMs that we test regularly. That adds up to a lot of data.
A few years ago, it wouldn’t have been feasible to accumulate data at that scale. But now that computing and storage costs make it feasible, the AVM builders themselves are enthusiastic about it. They like the idea of a fair and square competition. We now have valuations for every property BEFORE it’s sold, and in fact, before it’s listed.
As we have for well over a decade now, we gather actual sales to use as the benchmarks against which to measure the accuracy of the AVMs. We scrub these actual sales prices to ensure that they are for arm’s-length transactions between willing buyers and sellers — the best and most reliable indicator of market value. Then we use proprietary algorithms to match benchmark values to the most recent usable AVM estimated value. Using our massive database, we ensure that each model has the same opportunity to predict the sales price of each benchmark.
AVMetrics next performs a variety of statistical analyses on the results, breaking down each individual market, each price range, and each property type, and develops results which characterize each model’s success in terms of precision, usability, error and accuracy. AVMetrics analyzes trends at the global, market and individual model levels. We also identify where there are strengths and weaknesses and where performance improved or declined.
In the spirit of continuous improvement, AVMetrics provides each model builder an anonymized comprehensive comparative analysis showing where their models stack up against all of the models in the test; this invaluable information facilitates their ongoing efforts to improve their models.
Finally, in addition to quantitative testing, AVMetrics circulates a comprehensive vendor questionnaire semi-annually. Vendors that wish to participate in the testing process answer roughly 100 parameter, data, methodology, staffing and internal testing questions for each model being tested. These enable AVMetrics and our clients to understand model differences within both testing and production contexts. The questionnaire also enables us and our clients to satisfy certain regulatory requirements describing the evaluation and selection of models (see OCC 2010-42 and 2011-12).
Appraisals are the gold standard when it comes to valuing residential real estate, but they aren’t always necessary. They’re expensive and time-consuming, and in the era of COVID-19, they’re inconvenient. What’s the alternative?
Well, Fannie and Freddie implemented a “Property Inspection Waiver” (PIW) alternative more than a decade ago. However, it’s been slow to catch on.
But now, maybe the tipping point has arrived during the pandemic. Recently published data by Fannie and Freddie show approximately 33% of properties were valued without a traditional appraisal! (Most, if not all, would have used an AVM as part of the appraisal waiver process.) Ed Pinto at AEI’s Housing Center calls it a hockey stick.
So, what changed? Here are some thoughts and hypotheses:
Accurate AVMs are a necessary but not sufficient criteria for PIWs, and now that AVMs are much more accurate, PIWs are much more practical, and we’re seeing much higher adoption.
So now what should we expect going forward? The trend will likely continue. There’s a lot of room left in some of those categories for PIWs to grab a larger share.
If agencies are doing it, everyone else will. If there are lenders not using PIWs to the extent possible, they are going to be at a disadvantage.
AVMs are not only fairly accurate, they are also affordable and easy to use. Unfortunately, using them in a “compliant” fashion is not as easy. Regulatory Bulletins OCC 2010-42 and OCC 2011-12 describe a lot of requirements that can be challenging for a regional or community institution:
The extent to which these requirements are applied by your regulator is most likely proportional to the extent to which AVMs are used within your organization; if AVMs are used extensively, regulatory oversight will likely demand much tighter adherence to the requirements as well as much more comprehensive policies and procedures.
Although compliance itself is not a function that can be outsourced (it is the sole responsibility of the institution), elements of the regulatory requirements can be effectively handled outside the organization through outsourcing. As an example, the first bullet point, “ongoing independent testing and validation and documentation of testing,” requires resources with the competencies and influences to effectively challenge AVM models. In addition, the “independent” aspect is challenging to accomplish unless a separate department within the institution is established that does not report up through the product and/or procurement verticals (e.g. similar to Audit, or Model Risk Management, etc.). Whether your institution is a heavy AVM user or not, the good news is that finding the right third-party to outsource to will facilitate all of the bullet points above:
Before deciding whether outsourcing makes sense for you, here are some potential considerations. If you can answer “no” to all of these questions, then outsourcing might be a good option, especially if you don’t have an independent Analytics unit in-house that has the resource bandwidth to accommodate the AVM testing and validation processes:
The Way Forward
Here are some suggestions on how to go about preparing yourself for selecting your outsource partner:
In Conclusion
AVM testing and validation is only one component in your overall Valuation and evaluation program. Unlike Appraisals and some other forms of collateral valuation, AVMs, by their nature as a quantitative predictive model, lend themselves to just the type of statistically-based outcomes analysis the regulators set forth. Recognizing this, elements of the requirements can be an outsourced process, but it must be a compliment to enterprise-wide policies and practices around the permissible, safe and prudent use of valuation tools and technologies.
The process of validating and documenting AVMs may seem daunting at first, but for the past 10 years AVMetrics has been providing ease-of-mind for our customers, whether as the sole source of an outsourced testing and validation process (that tests every commercial AVM four times a year), or as a partner in transitioning the process in-house. Our experience, professional resources and depth of data have enabled us to standardize much of the processing while still providing the customization every institution needs. And probably one of the most critical boxes you can check off when outsourcing with AVMetrics is the very large one that requires independence. It also bears mentioning that having been around as long as we have, our customers have generally all been through at least one round of regulatory scrutiny, and the AVMetrics process has always passed regulatory muster. Regulatory reviews already present enough of a challenge, so having a partner with established credentials is critical for a smooth process.
Hit Rate is a key metric that AVM users care about. After all, if the AVM doesn’t provide a valuation, what’s the point? But savvy users understand that not all hits are created equal. In fact, they might be better off without some of those “hits.”
Every AVM builder provides a “confidence score” along with each valuation. Users often don’t know how much confidence to put in the confidence score, so we did some analysis to clarify just how much confidence is warranted.
In the first quarter of 2020, we grouped hundreds of thousands of AVM valuations from five AVMs by their confidence score ranges. For convenience’s sake, we grouped them into “high,” “medium,” “low” and “fuhgeddaboutit” (aka, “not rated”).[1] And, we analyzed the AVM’s performance against benchmarks in the same time periods. What we found won’t surprise anyone at first glance:
However, consider that unsophisticated users might simply use a valuation returned by an AVM regardless of the confidence score. One rationale is that any value estimate is better than nothing, and this is the valuation that is available. Other users may not know how seriously to take the “confidence score;” they may figure that the AVM supplier is simply hedging a bit more on this valuation.[2]
Figure 1 shows the correlation for Model #4 in our test between the predicted price and the actual sales price for each group of model-supplied confidence scores. As you can see, as the confidence score goes up so does the correlation[3] of the model and the accuracy of the prediction as evidenced by the drop in the Average Variance.
Table 1 lays out 4 key performance metrics for AVMs. They demonstrate markedly different performance for different confidence score buckets. For example, the “high” confidence score bucket for Model 1 performs significantly better in every metric than the other buckets, and what’s more that confidence bucket makes up 80% of the AVM valuations returned by Model 1.
This last metric mentioned is instructive. Model 1 is a very-high-performing AVM. However, in a certain small segment (about 3%), acknowledged by very low confidence scores, the model has a tendency to over-value properties by 20% or more almost one-third of the time.
The good news is that the model warns users of the diminished accuracy of certain estimates, but it’s up to the user to realize when to disregard those valuations. A close look at the table shows that with different models, there are different cut-offs that might be appropriate. Not every user’s risk appetite is the same, but we’ve highlighted certain buckets that might be deemed acceptable.
Model 2 and Model 5, for example, have very different profiles. Whereas Model 1 produced a majority of valuations with a “high” confidence level, Model 2 and Model 5 put very few valuations into that category. “Confidence scores” don’t have a fixed method of calculation that is standardized between Models. It’s possible that Model 2 and Model 5 use their labels more conservatively. That’s one more reason that users should test the models that they use and not simply expect them to perform similarly and use labels consistently.
That leads into a third conclusion that leaps out of this analysis. There’s a huge advantage to having access to multiple models and the ability to pick and choose between them. It’s not immediately apparent from this analysis, but these models are not all valuing the same properties with “high” confidence (this will be analyzed in two follow-up papers in this series). Model 4 is our top-ranked model overall. However, as shown in Table 2, there are tens of thousands of benchmarks that Model 4 valued with only “medium” or “low” or even “not rated” confidence but for which Model 1 had “high” confidence valuations.
Different models have strengths in different geographic areas, with different property types or even in different price ranges. The ideal situation is to have several layers of backups, so that if your #1 model struggles with a property and produces a “low” confidence valuation, you have the ability to turn to a second or third model to see if they have a better estimate. This last point is the purpose of Model Preference Tables®. They specify which model ranks first second and third across every geography, property type and price tranche. And, users may find that some models are only valuable as a second or third choice in some regions, but by adding them to the panel, the user can avoid that dismal dilemma: “Do I use this valuation that I expect is awful – what other choice do I have?”
[1] We grouped valuations as follows: <70% were considered “not rated,” 70-80% were considered “low,” 80-90% “medium,” and 90+ “high.”
[2] In fact, this isn’t wrong in some cases. For example, in the case of Model 2, the “medium” and “high” confidence valuations don’t differ significantly.
[3] The correlation coefficient indicates the strength of the relationship between two variables can be found using the following formula:
Where:
[4] Mean Error (ME)
[5] Mean Absolute Error (MAE)
[6] Percentage Predicted Error within +/- 10%
[7] Percentage Predicted Error greater than 20%, aka Right Tail Error
AVMetics’ ongoing independent AVM testing continues in 2020 according to the schedule in the link below. Please download the pdf with the entire 2020 testing schedule.
The AVMNews sat down with our publisher Lee Kennedy to discuss trends in the industry.
AVMNews: Lee, as the Managing Director at AVMetrics, you’re sitting at the center of the Automated Valuation Model (AVM) industry. What changes have you seen recently?
Lee: There’s a lot going on. We see firsthand how the evolution of the technology has affected the sector dramatically. The availability of data and the decline in costs of storage and computing power have opened the doors to new competition. We see new entrants using new techniques and built by fresh faces. We still have a number of large players offering well-established AVMs. But, we also see the larger players retiring some of their older models. The established AVM players have responded in some cases by raising their game, and in other cases, by buying their upstart rivals. So, we’ve seen increased competition and increased consolidation at the same time.
And, it’s true that the tools keep getting better. It’s not evenly distributed, but on average they continue to do a better and better job.
AVMNews: In what ways do AVMs continue to get better?
Lee: AVMetrics has been conducting contemporaneous AVM testing for over a decade now, and we have many quantitative metrics showing how much better AVMs are getting. Specifically, we run statistical analysis around the comparison of AVM estimates to sales prices that are unknown to the models. We have seen increases in model accuracy rates measured by percentage of predicted error (PPE), mean absolute error (MAE) and a host of other metrics. Models are getting better at predicting sale prices and when they miss, they don’t miss by as much as they used to.
AVMNews: What about on the regulatory side?
Lee: There is always a lot going on. The regulatory environment has eased in the last two years reflecting a whole new attitude in Washington, D.C. – one that is more open to input and more interested in streamlining. Take, for instance, the 2018 Treasury report that focuses on advancing technologies (See “A Financial System That Creates Economic Opportunities”).
Last November, I was at a key stakeholder forum for the Appraisal Subcommittee (ASC). One area of focus was harmonizing appraisal requirements across agencies. Another major focus was how to effectively employ new tools in support of the appraisal industry, including the growth of Alternative Valuation Products that utilize AVMs.
AVMNews: I know that you also wrote a letter to the Federal Finance Institutions Examination Council (FFIEC) about raising the de minimis threshold, below which some lending guidelines would NOT require an appraisal. This year in July they elected to change the de minimus threshold from $250,000 to $400,000 for residential housing. What are your thoughts?
Lee: Well, I think that the question everyone is struggling with is “What does the future hold for appraisers and AVMs?” Obviously, the field of appraisers is shrinking, and AVMs are economical, faster and improving. How is this going to play out?
First, my strong feeling is that appraisers are a valuable and limited resource, and we need to employ them at their highest and best use. Trying to be a “manual AVM” is not their highest and best use. Their expertise should be focused on the qualitative aspects of the valuation process such as condition, market and locational influences, not the quantitative (facts) such as bed and bath counts. Models do not capture and analyze the qualitative aspects of a property very well.
Several companies are developing ways of merging the robust data processing capabilities of an AVM with the qualitative assessment skills of appraisers. Today, these products typically use an AVM at their core and then satisfy additional FFIEC evaluation criteria (physical property condition, market and location influences) with an additional service. For example, the lender can wrap a Property Condition Report (PCR) around the AVM and reconcile that data in support of a Home Equity Line of Credit (HELOC) lending decision. This type of hybrid product offering is on the track that we’re headed down. Many AMCs and software developers have already created these types of products for proprietary use or for use on multiple platforms.
AVMNews: AVMs were supposed to take over the world. Can you tell us what happened?
Lee: Well, the Financial Crisis is one thing that happened. Lawsuits ensued, and everyone got a lot more conservative. And, the success of AVMs developed into hype that was obviously unrealistic. But, AVMs are starting to gain traction again. We are answering a lot more calls from lenders who want help implementing AVMs in their origination processes. They typically need our help with policies and procedures to stay on the right side of the Office of the Comptroller of the Currency (OCC) regulations, and so in the last year, we’ve done training at several banks.
Everyone is quick to point out that AVMs are not infallible, but AVMs are pretty incredible tools when you consider their speed, accuracy, cost and scalability. And, they are getting more impressive. Behind the curtain the models are using neural networks and machine learning algorithms. Some use creative techniques to adjust prices conditionally in response to situational or temporary conditions. We test them and talk to their developers, and we can see how that creativity translates into improved performance.
AVMNews: You consult to litigants about the use of AVMs in lawsuits. How do you think legal decisions and risk will affect the use of AVMs?
Lee: This is an area of our business, litigation support, where I am restricted from saying very much. It has been and continues to be an enlightening experience as some of the best minds are involved in all aspects of collateral valuation and the “Experts” are truly that… experts in their fields as econometricians, statisticians, appraisers, modelers, etc.… It is also very interesting with over 50 cases behind us now, to get a look behind the legal system curtain and how all of that works. Therefore, I want to emphasize that my comments for our interview are in the context of contemporaneous AVMs that were tested during the time period shown here and not a retrospective AVM that was looking back to these time periods.
AVMNews: AVMetrics now publishes the AVM News – how did that come about?
Lee: As you and the many subscribers know, Perry Minus of Wells Fargo started that publication as a labor of love over a decade ago. When he retired recently, he asked if I would take over as the publisher. We were honored to be trusted with his creation, and we see it as a way to be good citizens and contribute to the industry as a whole.
AVMNews: I encourage anyone interested in receiving the quarterly newsletter for free to go to http://eepurl.com/cni8Db
The AVMNews is a quarterly newsletter that is a compilation of interesting and noteworthy articles, news items and press releases that are relevant to the AVM industry. Published by AVMetrics, the AVMNews endeavors to educate the industry and share knowledge about Automated Valuation Models for the betterment of everyone involved.
Headline for Lynn Kennedy’s Market Summary
Lynn Kennedy, a contributing consultant at AV Metrics, provides us the Market Summary for Los Angeles County featured in Mobility Magazine, July 2019.
Learn more about Mobility Magazine, the magazine of the Worldwide ERC, dedicated to professionals involved in talent mobility. www.worldwideerc.org
As always, changes are coming to the valuation industry. These changes have been germinating in government and industry for a long time, but they’ve made progress in the last year, and I believe that they’re likely to emerge sometime this year. I expect that we may see more regulatory changes liberalizing the use of AVMs soon.
I think that you’ll come to that same conclusion, too, if I share a couple milestones that I’ve observed and put them together with some insights I’ve gathered from talking to industry leaders.
The first milestone I will highlight was the July 2018 Financial System report by Secretary Mnuchin, which is consistent with the administration’s new attitude towards regulation. The report is far-reaching, and it includes thoughtful commentary about the uses of AVMs (see, for example, page 103-106). It recommends updating FIRREA appraisal requirements to accommodate increased usage of AVMs and hybrids. It also advocates for increased monitoring of AVMs and the application of rigorous market standards. And, it recommends focusing the use of AVMs and hybrids on loan programs with other mitigating risk factors.
The next milestone I will highlight was the proposed change in the de minimis threshold that was put out for comment in November of last year. The change would raise the threshold below which a residential mortgage could be originated with an evaluation, utilizing an AVM in lieu of a traditional appraisal. It would be raised from $250,000 to $400,000.
To those milestones I would add a third data point. Last November I attended the Appraisal Subcommittee roundtable entitled: “The Evolving Real Estate Valuation Landscape.” As part of the of the Federal Financial Institutions Examination Council, the roundtable brought together industry representatives and government officials (see the table below) to discuss real estate valuation.
The day was split into two sessions; the morning and afternoon sessions each began with a panel of industry experts who addressed a series of prepared questions. In addition, there was a roundtable discussion focused on quotes from the July 2018 Financial System report referenced above.
The topic for the morning discussion was “Harmonizing Real Estate Valuation Requirements Across the Federal Government.” This session focused on identifying various federal appraisal statutory and regulatory requirements and exploring opportunities to harmonize those requirements, e.g., VA, FHA, and FHFA all having differing valuation requirements and standards.
The afternoon panel discussion topic was; “The Evolution of Real Estate Valuation” which focused on evolving valuation needs in commercial and mortgage lending. A key area of this session was focused on Alternative Valuation Products inclusive of AVM’s and their increasing used by lenders and the secondary market.
The roundtable discussion started with quotes about AVMs and hybrid valuation products and focused on standards. The group also contemplated how alternative valuation techniques can impact quality and mitigate risk. Finally, one quote that focused on speeding the adoption of technology was discussed.
As I write this six months later, I see the pieces of the puzzle coming together. Obviously, there is momentum behind the increased usage of AVMs, for their independence, increasing accuracy, speed and efficiency. But there is also an implicit concern to avoid opening the door to more risk. I see this being expressed by talk about “standards,” alternative products, such as “hybrids” and increased monitoring.
As I have written elsewhere, I welcome changes that make better use of our valuable and limited resources, namely the appraisers themselves. As AVM quality improves and the number of appraisers shrinks, we should encourage appraisers to be focused on their highest and best use. Their expertise should be focused on the complex, qualitative aspects of property valuation such as the property condition and market and locational influences. They should also be focused on performing complex valuation assignments in non-homogeneous markets. Trying to be a “manual AVM” is not the highest and best use of a highly qualified appraiser, and I expect that Treasury, the FDIC and legislators are moving in this same direction.
Lee Kennedy
| Participants in “The Evolving Real Estate Valuation Landscape” Appraisal Subcommittee, Federal Financial Institutions Examination Council, 2018 | ||
| Government | Trade Organizations | Industry Participants |
| The Appraisal Foundation (TAF) | American Bankers Association | AVMetrics, LLC |
| Association of Appraiser Regulatory Officials (AARO) | American Society of Appraisers | Bank of America |
| Consumer Financial Protection Bureau (4) | American Society of Farm Managers and Rural Appraisers | Clarocity Valuation Services |
| Federal Deposit Insurance Corporation(3) | Appraisal Institute | ClearBox |
| Federal Housing Finance Agency(4) | Homeownership Preservation Foundation | CoreLogic |
| Federal Reserve Board(5) | Independent Community Bankers of America | Cushman & Wakefield Global Services, Inc. |
| Freddie Mac | Mortgage Bankers Association | Farm Credit Mid-America |
| Internal Revenue Service | National Association of Home Builders | First American Mortgage Solutions |
| National Credit Union Administration | National Association of Realtors | Genworth Financial |
| Office of the Comptroller of the Currency (4) | Real Estate Valuation Advocacy Association (REVAA) | JPMorgan Chase & Company |
| Tennessee Real Estate Appraisers Commission | State appraiser coalitions representative | Old Line Bank |
| Texas Appraiser Licensing and Certification Board | Quicken Loans | |
| U.S. Department of Agriculture | ServiceLink | |
| U.S. Department of Justice (2) | ||
| U.S. Department of the Interior (2) | ||
| U.S. Department of Veterans Affairs | ||
| US. Department of Housing and Urban Development |
After determining that a transaction or property is suitable for valuation by an Automated Valuation Model (AVM), the first decision one must make is “Which AVM to use?” There are many options – over 20 commercially available AVMs – significantly more than just a few years ago. While cost and hit rate may be considerations, model accuracy is the ultimate goal. A few additional estimates that are off by more than 20 percent can seriously increase costs. Inaccuracy can increase second-looks, cause loans not to close at all or even stimulate defaults down the road.
Which is the best AVM?
We test the majority of residential models currently available, and in the nationwide test in Figure #1 below, Model AM-39 (not its real name) was the top of the heap. It has the lowest average (absolute) error (MAE) by .1 over the 2nd place model. Model AM-39 is a full percentage point better than the 5th ranked model, which is good, but that’s not everything. Model AM-39 has the highest percentage of estimates within +/- 10% (PPE10%). Model AM-39 has the 2nd lowest percentage of extreme overvaluations (>=20%, or RT20 Rate), an especially bad type of error indicating a significant overvaluation or Right Tailed error.
If you were shopping for an AVM, you might think that Model AM-39 is the obvious choice. This model performs at the top of the list in just about every measure, right? Well, not so fast. Consider that those measurements are based on testing AVM’s across the entire nation, and if you are only doing business in certain geographies, you might only care about which model or AVM is most accurate in those areas. Figure 2 shows a ranking of models in Nevada, and if your heart was set on Model AM-39, then you would be relieved to see that it is still in the top 5. And, in fact, it performs even better when limited to the State of Nevada. However, three models outperform Model AM-39, with Model X-24 leading the pack in accuracy (albeit with a lower Hit Rate).
So, now you might be sold on Model X-24, but you might still look a little deeper. If, for example, you were a credit union in Clark County, you might focus on performance there. While Clark County is pretty diverse, it’s quite different from most other counties in Nevada. In this case, Figure 3 shows that the best model is still, Model X-24, and it performs very well at avoiding extreme overvaluations.
However, if your Clark County Credit Union is focused on entry level home loans with properties values below $100K, you might want to check just that segment of the market. Figure 4 shows that Model X-24 continues to be the best performer in Clark County for this price tier. Note that the other top models, including Model AM-39, show significant weaknesses as their overvaluation tendency climbs into the teens. This is not a slight difference, and it could be important. Model AM-39 is seven times more likely than Model X-24 to overvalue a property by 20%, and those are high-risk errors.
Look carefully at the model results in Figure 4 and you’ll see that Model X-24, while being the most accurate and precise, has the lowest hit rate. That means that about 40% of the time, it does not return a value estimate. The implication is: you really want a second and a third AVM option.
Now let’s consider a different lending pattern for the Clark County credit union. Consider a high value property lending program and look at figure 5, which is an analysis of the over-$650K properties and how the models perform in that price tier. Figure 5 shows that Model X-24 is no longer in the top five models. The best performer in Clark County for this price tier is Model AM-39, with 92% within +/-10% and zero overvaluation error in excess of 20%. The other models in the top five also do a good job of valuing properties in this tier.
Figure 6 summarizes this exercise, which demonstrates the proper thinking when selecting models. First, focus on the market segment that you do business in – don’t use the model that performs best outside your service area. Second, rather than using a single model, you should use several models prioritized into what we call a “Model Preference Table®” in which models are ranked #1, #2, #3 for every segment of your market. Then, as you need to request an evaluation, the system should call the AVM in the #1 spot, and if it doesn’t get an answer, try the next model(s) if available.
In this way, you get the most competent model for the job. Even though one model will test better overall, it won’t be the best model everywhere and for every property type and price range. In our example, the #1 model in the nation was not the preferred model in every market segment we focused on. If we had focused on another geography or market segment, we almost certainly would have seen a reordering of the rankings and possibly even different models showing up in the top 5. The next quarter’s results might be different as well, because all the models’ developers are constantly recalibrating their algorithms; inputs and conditions are changing, and no one can afford to stand still.
