ATTOM LAUNCHES AI-POWERED AVM BUILT ON 30 YEARS OF PROPERTY INTELLIGENCE

Next-generation model leverages 30+ years of data and advanced AI to achieve 2.9% median error across 98 million U.S. properties

IRVINE, Calif., May 5, 2026 /PRNewswire/ -- ATTOM, the leading provider of property data, AI-powered analytics, and real estate intelligence solutions, today announced the launch of its next-generation automated valuation model (AVM), a ground-up, AI-first rebuild designed to move beyond the limitations of traditional comparable-sales-based valuation models.

Traditional AVMs rely heavily on recent comparable sales, which limits accuracy in today's low-transaction housing market. ATTOM's new model replaces this dependency with an AI-driven approach that leverages more than 30 years of time-adjusted transaction history, enabling more reliable valuations for underwriting, portfolio analysis, and risk management, particularly in markets where traditional AVMs struggle.

The result is a valuation system that learns how markets evolve over time by analyzing relationships between property characteristics, historical pricing patterns, and hyperlocal trends to generate accurate, property-level valuations even in low-liquidity or data-sparse environments.

Through iterative out-of-sample testing across the past decade of residential sales, the ATTOM AVM consistently delivered a median absolute percentage error of 2.9%, with more than 80% of valuations falling within 10% of the actual sale price.

"This is not an incremental improvement—it's a complete re-architecture of the AVM using advanced AI," said Rob Barber, CEO at ATTOM. "We've moved beyond static, comp-based approaches to a dynamic system that can learn from decades of market behavior and adapt to changing conditions in real time."

"We model how each neighborhood has evolved over the past 30 years and use that temporal context to translate historical sales into accurate present-day values. This gives our valuation system a richer foundation to learn from, allowing each model to synthesize property characteristics, local market dynamics, and price history into a single, informed estimate. The result is consistent accuracy, even in markets where traditional comparable-sales approaches tend to break down," said Aaron Wagner, Vice President of Data Science at ATTOM.

Each valuation includes a confidence score that provides a clear signal of reliability, enabling organizations to automate decisions with greater control and transparency.

The ATTOM AVM is built for enterprise use across mortgage, insurance, investment, and proptech applications, and is delivered through flexible solutions including APIs, bulk delivery, and cloud platforms such as Snowflake and Databricks.

A detailed technical white paper describing the AVM's methodology, confidence framework, and accuracy benchmarks is available here.

About ATTOM
ATTOM delivers AI-driven property intelligence built on one of the nation's most trusted property data assets, covering 160 million U.S. properties—99% of the population. Our engineered, multi-sourced real estate data spans property tax, deeds, mortgages, foreclosure, environmental risk, property conditions, natural hazards, neighborhood insights, and geospatial boundaries, rigorously validated for advanced analytics. ATTOM supports analytics and AI-driven applications through flexible delivery options including APIs, bulk licensing, cloud delivery, market trend products, and the MCP Server for AI-powered, agentic access to engineered property data—enabling organizations to automate analysis and scale property intelligence across industries.

Media Contact:
Megan Hunt
[email protected]

Data and Report Licensing:
[email protected]

SOURCE ATTOM