Zillow taps AI to improve its home value estimates

people stories Getting cash offers on their homes in the tens of thousands of dollars over the asking price has become the norm. This year, the inventory in the US housing market hit a record low while home prices hit a record high. Redfin CEO Glenn Kellman recently highlighted the madness with a tweet It tells the story of a home buyer who offered to name their first child after the seller’s name – and was refused.

With the US housing market starting to heat up, in February Zillow began offering initial cash offers for home purchases based on its price estimate. Now Zillow has updated a file algorithm behind those estimates in a way the company says will make them more accurate — and allow Zillow to offer to buy more homes.

Owners of about 900,000 properties were initially eligible to receive automatic cash offers to purchase a home. Stan Humphries, chief analytics officer at Zillow, said the change to the device Artificial intelligence It will expand this pool by 30 percent. A company spokesperson said Zillow’s offerings can close sales in as little as one week.

Zillow pre-determines the value of homes using nearly 1,000 different types of algorithms derived for local markets. Now all prices nationwide will be determined by one neural network. Zillow says the new algorithm will reduce price estimation errors by 11.5 percent for off-market homes in nearly 30 areas across the United States. Compared to the previous version of the algorithm, errors decreased most in Phoenix, followed by San Antonio, Tampa, and Houston.

Using the new algorithm, Zillow will frequently update its estimates of the value of 104 million properties in 23 US markets. Around the time the company was founded in 2005, ratings were updated monthly. Recently, it has been updated several times a week; Now, some estimates may be updated daily.

Zillow’s home estimates are a common topic in local conversations, particularly in hot housing markets. a Last Saturday Night Live A skit compared surfing Zillow to phone sex and joked that, for people in their late thirties, “the pleasure I once got from sex now comes from looking at other people’s homes.”

Zillow has been developing a home valuation algorithm for 15 years. The move toward a single neural network began in 2019 after a public competition to improve its estimates that attracted more than 3,000 teams competing for the $1 million prize. Two out of three contestants in this competition used neural network-based methods, a form of deep learning that Zillow says is better able to recognize the relationship between the data used to estimate the home rating.

For example, Humphreys said the new approach is better able to understand the value of a waterfront property or how valuations are affected by the size of neighboring homes.

“The old-fashioned approach will find it difficult for that county to understand the value of waterfront homes,” he said. “Neural networks trained in the whole country can get information from other parts of the country about the value of the waterfront and apply it in a local geographic area, even if there are not many such homes in that geographic area.”

Home value estimates are based on dozens of factors about the property, including square feet and location. Some listings also include data from tax assessments and sales records. Since 2016, the company has also used computer vision systems that draw inferences from photos of home listings.

By expanding its home-buying program, the company’s CEO Rich Barton said the company hopes to bring one-click e-commerce sensitivity to the real estate market. “Ultimately we want to have the most homes in the country inside the live view purchase fund,” he said.

The company also hopes to benefit from what it calls a “big change,” as more people look to work from home more often, and millennials look to buy homes.

Billions of people look at Zillow’s lists each year, Barton says, to dream or engage in a little voyeurism. For them, Zillow is trying to “engage or entertain,” but for people who buy and sell homes, Zillow wants to sell more services. In addition to home purchases, Zillow also ramps up services such as home loans, home insurance, and help with the escrow process.

More great wired stories

Source link

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button