Zillow’s home valuation tool Zestimate is being improved with new innovations contributed in part by a Canadian data scientist.
Nima Shahbazi entered the real estate listings’ firm’s two-year-lomg competition to improve the 13-year-old Zestimate along with Moroccan collaborator Chahhou Mohamed.
They were later joined by Jordan Meyer in the United States and the three worked across time zones in a bid to beat the algorithm that changed real estate.
Their winning innovations beat the Zillow benchmark model by approximately 13% and won the trio the $1 million first prize.
"It's amazing to know that millions of people will benefit from our ideas," said Nima Shahbazi, one of the winning team members. "We brought every novel idea we could to our code and kept experimenting. For every idea that worked, there were a hundred that didn't work. But we kept going."
Along with innovations from teams that also won cash prizes, the trio’s work will now be incorporated into an improved Zestimate with the aim of reducing the error rate from 4.5% to below 4%.
Based on Zillow’s December US median home price of $223,900, it’s estimated that the estimated value would be $1,300 closer than the current $10,000 average off the actual sale price of a typical home.
"People are incredibly passionate about their home and understanding its value, and we are amazed by the winning team's hard work the past two years to make the Zestimate even more precise," said Stan Humphries, chief analytics officer and creator of the Zestimate. "We've been on a 13-year journey making the Zestimate more accurate, and hosting Zillow Prize allowed us to invite thousands of brilliant data scientists from around the world to join us on this journey. We're so proud that the winning team's huge achievement, and the work of all the teams in the competition, will provide millions of homeowners with a better understanding of one of their biggest life investments."
More market update: