Automated Valuation Models (AVMs) have come a long way from the rudimentary tools of the mid-1990s to where the industry is today. More extensive and more refined data has become available and consumable by modelers who can now employ highly sophisticated modeling techniques to test and build the modern AVM. Together with the vast expansion of technology and data management, today’s data scientists and modelers are able to instantaneously process, test and refine incredible amounts of data in the Cloud using tools like artificial intelligence and machine learning to produce higher levels of confidence and reliability. In many cases, AVM developers use back testing, the method in which machine-learning techniques are used to “teach” the model, to prove their efficacy against closed loan data, list price, sale price and property characteristics data.
More than 25 AVMs have come to market in the past 25 years as modelers are leveraging more expansive property data and modeling techniques to test their assumptions that a new model can produce more accurate valuations. With the evolution of technology and computing power, specific use cases for AVMs outside of traditional lending uses are now becoming mainstream in real estate, marketing and consumer online experiences. Each of these participants all have very different needs and modelers now can provide an AVM that is best suited for each purpose.
Today, there are three general grades of AVMs commonly available: marketing, consumer-facing, and lender grade. The most effective AVMs use multiple sets of data and sub-models, running on a base of multiple listing service (MLS) listing data and public record assessor data. What distinguishes one model from another is how the data, and how much of the data, is used. For example, if you’re using an AVM for marketing purposes, you may want a model that has the highest hit rate, so that every property shows at least a rough value. To attain a higher hit rate, marketing AVMs may generate valuations using less data and fewer comparables (comps) and include fewer property characteristics. However, a lender-grade model may not produce a value for that same property due to a lack of available information needed to generate a value with the desired confidence score.
Let’s start with what most in our industry consider a “full” AVM. Lender-grade AVMs serve a critical role in the determination as to whether to underwrite a purchase or refinance loan transaction. They include multiple data sources to produce a valuation with a high-confidence score. These more sophisticated AVMs frequently layer in multiple sub-models, including regression analysis, appraisal emulation, data mining, current and historical market performance in the area, and the latest machine-learning modeling techniques. The sub-model results are then blended, weighted and reconciled by a final model to produce the property valuation. In some cases, and in increasing numbers, this type AVM is being used in lieu of a full appraisal and can require only a drive-by or desktop appraisal for some low loan-to-value (LTV) refinances.
Lender-grade AVMs are also used by servicers and investors to manage portfolios to identify risks; assist in distress asset management and disposition; or to help make buy/sell decisions
This AVM is designed to provide a value on 100% of properties at an extremely low cost per property, delivering valuations with a high hit rate and an acceptable level of accuracy. These models often sacrifice some degree of accuracy to attain the extremely high hit rate, as they use fewer comps and characteristics than higher-grade AVMs. Lenders often use a marketing model AVM to identify prospects for home equity lending based on an estimate of the current loan-to-value of a property.
Similarly, these models can be used by a variety of home improvement companies and retailers targeting potential prospects for direct marketing offers to replace or repair the property’s existing roof, pool, HVAC, landscaping, or other improvements and purchases.
Consumer-facing models are used extensively in online real estate and lending portals. They offer a quick reference tool to help consumers understand what a home is worth and what potential financing options might be for a certain property. Online lenders, PropTech firms and iBuyers use these types of “white-labeled” AVMs to engage consumers for prospecting, initial screening and to instantly channel prospects to the appropriate product. These AVMs also provide a high hit rate, but with looser tolerances since no underwriting requirements are built into the model. They also can include owner-stated property conditions, upgrades and past appraisal results.
The Next Step for AVMs
The latest AVMs are using new sources of data that are harder to acquire. These can include geo-spatial characteristics, true neighborhood boundary information and the “holy grail” of AVM modeling – the current condition and quality of the property versus similar properties in the comparable geographic area. Many valuation experts believe the increasing availability of property condition and quality data will produce a paradigm in future AVM development.
The convergence of cloud computing and new data sources and extraction techniques with access to property condition and quality data will enable AVM performance to reach new heights. Many observers believe that this new generation of AVMs will be realized in the not-too-distant future. At First American Data & Analytics, we’ll be leading the development to understand how these models will change use cases, adoption and the future of valuation.
For additional information about First American Data & Analytics' AVM offerings, visit Procision™ AVM.