Automated valuation models (AVMs), which allow for contact-free assessment of a home’s market value, hold great promise for reducing the costs and increasing the accuracy of home valuations. They have also been critical to supporting the real estate market during the COVID-19 pandemic. But AVMs in majority-Black neighborhoods produce larger errors, relative to the underlying sales price, than AVMs in majority-white neighborhoods, potentially contributing to the wide housing wealth gap between Black and white homeowners. By refining the current AVM, this valuation disparity could be eliminated, and the benefits of homeownership could be more equitably available to all homeowners.