Monday, June 8, 2026

ATTOM launches AI-Powered AVM 

ATTOM announces the launch of its next-generation automated valuation model (AVM).

ATTOM, providers of property data, AI-powered analytics, and real estate intelligence solutions announces 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 over 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.

“This is not an incremental improvement – it’s a complete re-architecture of the AVM using advanced AI. We’ve moved beyond static, comp-based approaches to a dynamic system that can learn from decades of market behaviour and adapt to changing conditions in real time.”

Rob Barber, CEO, ATTOM

The result is a valuation system that learns how markets evolve over time by analysing 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 over 80% of valuations falling within 10% of the actual sale price.

“We model how each neighbourhood 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.” 

Aaron Wagner, Vice President of Data Science, ATTOM

Each valuation includes a confidence score that provides a clear signal of reliability, enabling organisations 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.

Deviki Patel
Deviki Patel
Deviki is a Digital Journalist at AI PropTech News, Rental Living News and BTR News. She holds a BA (Hons) in Law and an LLM from the University of Leicester. Having transitioned from a background in property law, she brings a strong foundation in research and analytical thinking, supporting the delivery of well-informed, insight-led content across the Living and PropTech sectors.

Related Articles

Latest Articles