Zillow Group uses machine learning to improve Zestimate algorithm for changing market trends
Seattle real estate giant Zillow Group announced new tweaks to its Zestimate tool that provides home value data on more than 104 million properties. The company now uses machine learning-based neural networks and additional data that improve how quickly the algorithm reacts to market trends.
Zillow said Zestimate’s national median error rate for off-market homes is now 6.9%, an improvement of nearly a full percentage point. The median error rate for on-market homes is 1.9%.
Using neural networks was a technique used in 2019 by the winners of the ZIllow Prize, a competition to improve the Zestimate.
Zillow launched the Zestimate in 2006. It marked the first time that homeowners gained access to estimated home values — data that was previously only available to real estate agents, appraisers and mortgage lenders.
Some have criticized the tool over the years. A group of homeowners in Illinois sued Zillow in 2017, alleging that the Zestimate tool is often inaccurate and difficult to get changed, and that Zillow markets it as roughly equivalent to an appraisal. The homeowners argued that the tool undervalued their homes and made it harder for them to sell. A federal appeals court sided with Zillow in the lawsuit.
Zillow is now using the Zestimate to make cash offers on homes, part of the company’s new focus on the end-to-end home-buying and selling experience.