Artificial intelligence tool makes valuing land and property more efficient and accurate

Researchers from the UNSW Built Environment City Analytics Lab are leading a project that will help homebuyers and investors make efficient and accurate land and property valuations.

Housing near Sydney's CBD

Aerial view of housing near Sydney's CBD. Photo: Shutterstock.

Researchers from UNSW Sydney’s Faculty of Built Environment are leading a collaborative project that is revolutionising the way land and property values are assessed in Australia.

UNSW Professor Chris Pettit, Chair of Urban Science and Director of the City Analytics Lab in the City Futures Research Centre, is working with partners from industry and government to develop Value Australia, a suite of products integrating research, data analytics and artificial intelligence to deliver efficient and accurate valuations for a broad range of land and property types across Australia and overseas. Partners on the project include FrontierSI, Commonwealth Bank, NSW Office of the Valuer General, Omnilink and Liverpool City Council.

Value Australia recently received $3 million in federal funding through a Cooperative Research Centre Project (CRC-P) grant. The project will provide better information about Australia’s $6.8 trillion property market sooner to homebuyers, investors, businesses and governments whilst reducing costs and risks.

It is designed to streamline the current labour-intensive approach to land and property value assessment that results in expensive, subjective, slow and out-of-date valuations, particularly for urban fringe and regional land.

“There will be a public-facing version of the software using a map interface to show property values around where people live, which will take into account land values and the amenity of an area,” Professor Pettit said. “It will assist in making data-driven decisions, such as the ability to explore rezoning options, determining the economic benefits of a development proposal, or even the location of important infrastructure, like new metro or light rail stations.”

The project builds on two years of pilot work across metropolitan Sydney and Brisbane through the award-winning Rapid Analytics Interactive Scenario Explorer (RAISE) project, which has developed a range of Automated Valuations Models (AVMs), the best of which aligns to market sales data to a 94 per cent accuracy. Building on this base, Value Australia will produce a national suite of data and software products over the next three years.

Pilot work has also allowed users to rapidly test the impact of new infrastructure development to determine the potential land valuation changes of this infrastructure within minutes. Multiple scenarios can be rapidly created and compared, further allowing decision makers to validate consulting reports.