ATTOM Launches AI Based Property Valuation Model Covering 98 Million Homes

May 5, 2026
ATTOM introduced a new AI powered automated valuation model built on 30 years of property data, achieving a 2.9 percent median error across 98 million US properties.

ATTOM has launched an automated valuation model built on three decades of property data and artificial intelligence, announced in a press release. The model covers 98 million US properties and reports a 2.9 percent median absolute percentage error in testing.

The valuation system is designed to overcome the limitations of traditional comparable sales models by learning from 30 years of time adjusted transaction history. It analyzes property characteristics, historical pricing, and local market trends to produce valuations even in markets with limited sales data.

Each valuation includes a confidence score that measures reliability. The model is available for use in mortgage, insurance, investment, and property technology applications. Delivery options include APIs, bulk data, and integration with cloud platforms such as Snowflake and Databricks.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Finance AI Weekly or Daily AI Brief.

Also, consider following us on social media:

AI in Finance AI Brief AI Brief (X)
Free newsletter

Finance AI Weekly

Weekly newsletter about AI in finance. Covers AI-driven trading, fintech innovations, and data analytics transforming markets

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.