Blog
Articles
Articles and announcements from AVMetrics.
FeaturedArticlesAVMetrics Completes Transition to Predictive Testing MethodologyAfter years of parallel testing, AVMetrics has formally retired its legacy AVM testing process. Predictive Testing Methodology (PTM™) is now the firm's sole testing platform, evaluating models against eventual sale prices using estimates produced before listing data ever reaches them — a method that aligns with regulatory expectations and reflects how AVMs are actually used in production.Read the article →FeaturedArticlesMISMO's Step in the Right Direction, The Common Confidence Score, Is Just One StepMISMO's Common Confidence Score standard gives the industry a shared definition of what an AVM confidence score should mean. But defining the target and verifying that models are hitting it are two different things — and the verification requires independent testing at a scale most institutions cannot achieve on their own.Read the article →FeaturedArticlesAO-41 and the Real Technology Question Appraisers Must AnswerAO-41 forces an uncomfortable but necessary question: What does competent reliance look like when the mechanics of the tool are outside the appraiser's control? The answer is independent, third-party testing—evidence from outside the model that appraisers can actually evaluate.Read the article →FeaturedArticlesWhy AVMetrics' Fair Housing Methodology Surpasses Vendor ApproachesVendor-published fair housing analyses represent early efforts to evaluate AVM bias, but they're inherently limited by their self-assessment nature. Each vendor tests only their own model and typically concludes little bias exists. AVMetrics' independent methodology conducts standardized, national testing across 700,000-1M quarterly transactions using Standardized Mean Difference metrics—delivering the regulatory-grade evidence lenders need to demonstrate compliance with new Interagency AVM Quality Control StandardsRead the article →FeaturedArticlesWhat DOJ’s Disparate-Impact Rollback Doesn’t Change About AVM FairnessThe Department of Justice’s recent move to eliminate disparate-impact liability under its Title VI regulations has raised understandable questions across housing and credit markets. But for lenders, GSE partners, and valuation providers preparing for the AVM Quality Control Standards , one thing is clear: The obligations around AVM fairness haven’t gone away. The interagency AVM…Read the article →FeaturedArticlesBest Practices for AVM Testing: Why Sale Prices Matter More Than Appraisal ValuesMany lenders use the "15% rule" for AVM-based quality control, assuming that when an AVM estimate aligns with an appraisal value, both are accurate. This widespread practice reveals a fundamental misunderstanding that could be undermining the entire valuation ecosystem.
The problem? Comparing AVMs to appraisals measures precision, not accuracy. This distinction isn't just semantic—it's the difference between knowing whether your valuations actually predict market value or simply agree with other estimates. When institutions use AVMs to validate appraisals in QC processes, then turn around and use those same appraisals to test AVM accuracy, they create a dangerous circular logic that masks true performance.
This article examines why the only meaningful benchmark for AVM accuracy is the actual sale price—the endpoint of market negotiation. We explore the critical importance of blind testing, MLS data suppression, and alignment with real-world use cases. Most importantly, we demonstrate how the Interagency Appraisal and Evaluation Guidance explicitly supports testing AVMs against actual sales data, not appraisal estimates.
Understanding this distinction is essential for lenders, AMCs, and AVM vendors who need to move beyond the comfort of circular validation to achieve genuine predictive accuracy.Read the article →FeaturedArticlesSetting the Record Straight on AVM Testing MethodologiesThis op-ed offers an affirmation of the core tenets of what is becoming the industry-standard testing framework: a data-driven testing methodology grounded in sound and prudent validation principles. While Veros challenges this approach, the broader AVM ecosystem—including regulators, lenders, and nearly all major AVM providers—have embraced a process that prioritizes objective, real-world performance measurements over now antiquated methods allowing for data leakage into the Automated Valuation Model.Read the article →FeaturedArticlesUsing Appraised Values vs. Arm’s-Length Transactions for Testing AVMsUsing appraisals seems like a great way to get more benchmarks for testing AVMs, and since AVMs and appriasals are trying to do the same thing: predict sales prices, it seems intuitively appealing. However, there are some fundamental problems with using appriased values to test AVMs. Appraised values are subjective and inconsistent, and they introduce bias and compound errors. This article explains why arms' length transactions are the only appropriate way to test AVMs. Read the article →FeaturedArticles#1 AVM in Each County Updated for Q4 2024We rank almost every AVM in the country, and this GIF shows how that ranking changes county by county throughout 2023 and 2024. Read the article →