ATTOM, AVM Analytics launch new valuation model

With many AVMs either too pricey or too diluted, ATTOM and AVM Analytics' new model targets "the big middle" between the two extremes

By Ryan Smith

26 Jun 2018

Property analytics company ATTOM Data Solutions and valuation software development firm AVM Analytics have announced the launch of ATTOMIZED AVM, a lender-grade automated valuation model. Valuations from the ATTOMIZED AVM are available for more than 80 million US homes, ATTOM said.

The valuation model is available through ATTOM’s various data delivery platforms – bulk file, API, match-and-append, custom reports, and ATTOM Lists.

“The new ATTMOMIZED AVM fills an important gap in the world of property valuation products that primarily reside on one of two extremes: Overpriced lender-grade AVMs that are only cost-effective for a few giant corporations, and free AVMs available to the masses but diluted due to their inherent need to be all-inclusive – not to mention they are typically not available to be delivered in bulk,” said Rob barber, CEO of ATTOM Data Solutions. “The ATTOMIZED AVM targets the big middle between those two extremes, providing the marketplace with a lender-grade AVM delivered via bulk data-delivery platforms that are flexible and cost-effective.”

The ATTOMIZED AVM employs multiple valuation models to calculate the estimated value of a home, then uses an algorithm to choose the approach that’s most accurate in the geographic area surrounding the property, ATTOM said. The model also excludes several types of properties that can have a negative impact on the predictive value of other homes and require more specific data and modeling. Some excluded property types are mobile homes, extremely high-end luxury homes, special-use properties, homes on farmland, and multi-unit homes with five or more units.

“What we exclude is important,” said Clifford A. Lipscomb, vice chair and co-managing director of AVM Analytics. “Not only do we exclude certain anomalous property types, but we also exclude the subject property itself, making our monthly accuracy tests a true out-of-sample comparison.”