The human intelligence out there in the real estate market says things are still sizzling; the artificial intelligence tools employed by Zillow are boosting business by as much as 30 percent.

Just four months back, Zillow green-lighted the idea to put forth cash offers to buy homes based on its price estimate. This month, Zillow provides the capability via AI to make those estimates more accurate and access the space to buy even more homes.

While 900,000 prospective homeowners had been given the go-ahead before, Zillow exec Stan Humphries said AI will push that number north by almost a third.

The evolution of the home-buying algorithm has gathered momentum, and Zillow now says the new algorithm will cut price-estimate errors by 11.5 percent for off-market homes. 

It’s all about accuracy. reports that, compared with the previous version of the algorithm, errors shrank the most in Phoenix, followed by San Antonio, Tampa, and Houston.

Potential buyers and sellers can’t get enough of this product, and Zillow promises more frequent updates of more than 100 million properties in 23 American markets. Those valuations were initially sent out monthly. Lately, it’s become common to see them updated virtually daily.

The new approach is better able to grasp the particulars.

“The old approach would have difficulty in that county understanding the value of waterfront homes,” he said. “Neural networks that are trained on the entire country could take information from other parts of the country about the value of waterfront and apply it in a local geography, even if there weren’t a lot of homes like that in that geography.”

Zillow is eyeing “the great reshuffling,” as it defines more people looking to work from home more often, and includes a shift for millennials who now are looking to buy homes.

Add comment