SEATTLE, March 1, 2018 /PRNewswire/ -- Today, Zillow® announces the top three teams from Round One of its Zillow Prize® competition who collectively will take home $50,000. Zillow first announced Zillow Prize in May 2017, and to date it's become one of the most popular machine learning competitions ever on Kaggle, with more than 3,800 teams representing 91 countries participating. Now, the top 100 teams have moved on to the Second Round, where they are competing for the million-dollar grand prize.

To qualify for the Second Round, teams had to improve the accuracy of the Zestimate® beyond the current error rate of 4.2 percent in the three competition counties¹. The top team was able to increase accuracy by 4.4 percent, achieving an overall rate of approximately 4 percent².

The top three teams include a team representing three different countries who have never met in-person and a father-daughter duo from Switzerland.

• FIRST PLACE: Team Zensemble was awarded the $25,000 first prize. The team is Russ Wolfinger (United States), Dmytro Poplavskiy (Australia), and Jonathan Gradstein (Israel), who first met online as competitors in another contest. Wolfinger plans to donate all his winnings from the first round to the math and science program at Meredith College, a women's liberal arts school in North Carolina, where his wife is the dean of Natural and Mathematical Sciences.
  
  "My family has three daughters, and we're really passionate about getting women involved in these hard-core STEM projects," Wolfinger said.
  
  For Poplavisky, his hard work on Zillow Prize also had an impact on his electric bill, as it doubled during the first round due to his uptick in server usage. To offset the cost, he installed solar panels on his Brisbane, Australia-based home.

• SECOND PLACE: Team Silogram-2 won the $15,000 second prize. This father-daughter duo worked on the competition from their home in Zurich, Switzerland. Phil Margolis, an independent consultant focusing on machine learning contract jobs, and his 21-year-old daughter Isabel Margolis, a student studying math and computer science in Zurich, became interested in the competition because it was a real-life scenario they could identify with. While they don't live together, they had the added benefit of being able to work together in-person from the Margolis family home.
  
  "I've bought and sold a home in the U.S., and you look at properties and there's all these theories about how to valuate them," Phil Margolis said. "This was really an interesting case where we could apply really advanced machine learning technology to real world data." The pair has not decided what they will do if they win the million-dollar prize. "I'll probably end up spending it on cloud server time," Phil Margolis joked.
  
  "I was excited to participate and team up with my dad on this contest," Isabel Margolis said. "I'm often outnumbered by men in my computer science classes, the ratio is about 20 percent female so it is very extreme. I wish more women would go into computer science."

• THIRD PLACE: Ryuji "Jack" Sakata was awarded the $10,000 third prize. A resident of Osaka, Japan, Sakata is one of many solo competitors in the contest. The 30-year-old data scientist has spent the past six years at Panasonic working to improve manufacturing using data analysis. He dabbled with programming in college but only ended up in his current role after he was randomly assigned to data science at the electronics company. He learned on the fly and has transferred those skills over to Zillow Prize, even though he's never visited the U.S.
  
  "I am not familiar with the U.S. housing market, but a challenge of creating a real forecast for the future was very interesting," he said. Sakata says he hasn't decided what he would do if he wins the million-dollar prize but imagines he might put it toward the purchase of a house in his hometown of Osaka.

Read more about the finalists competing for the Zillow Prize at www.zillow.com/promo/zillow-prize-first-round/.

"We've been blown away by the data science community's response to the Zillow Prize. There were lots of innovative solutions – and hundreds of teams were able to make incremental improvements in the Zestimate's accuracy. The Zestimate is trying to answer an incredibly complex and important question - how much is my home worth - and we're so excited to see what new innovations these top 100 teams bring to the Second Round," said Stan Humphries, creator of the Zestimate and Zillow Group's chief analytics officer. "We hope Zillow Prize not only inspires current data scientists to dive into the world of real estate valuations, but also inspires a future generation to consider a career in data science and machine learning. There's an incredible opportunity to bring new and diverse minds into the field."

Zillow is matching the first-round prize money with a $50,000 donation to #YesWeCode, a Dream Corps initiative. #YesWeCode helps 100,000 young women and men from underrepresented backgrounds find success in the tech sector. This is part of Zillow Group's greater efforts to support STEM-focused organizations which includes donations and investments in the University of Washington School of Computer Science and Engineering, DiscoverU, and the Washington State Opportunity Scholarship.

Second Round Began Feb. 1, 2018
The Second Round of Zillow Prize opened February 1, 2018, and the winners will be announced early 2019. In the Second Round, the winning team must build an algorithm to predict the actual sale price itself, using innovative data sources and imaginative solutions—involving everything from deep learning to hyperlocal data sets—to engineer new features that will give their model an edge over other competitors. The home value predictions from each algorithm submission will be evaluated against real-time home sales in August through October 2018.

To win the $1 million dollar grand prize, an algorithm must beat Zillow's benchmark accuracy on the Second Round competitions data set and enhance the accuracy further than any other competitor. The Zestimate's current margin of error is 4.5 percent, nationwide. A $100,000 second place prize and $50,000 third place prize will also be awarded to the top three ranking teams in the qualifying round.

Zillow publishes Zestimate home valuations on more than 100 million homes across the country based on 7.5 million statistical and machine learning models that examine hundreds of data points on each individual home.

To calculate the Zestimate home valuation, Zillow uses data from county and tax assessor records, and direct feeds from hundreds of multiple listing services and brokerages. Additionally, homeowners have the ability to update facts about their homes, which may result in a change to their Zestimate. More than 70 million homes on Zillow have been updated by the community of users. 

The Zillow Prize contest is being administered by Kaggle, a platform designed to connect data scientists with complex machine learning problems.  Zillow launched Zillow Prize in May 2017.

Zillow

Zillow is the leading real estate and rental marketplace dedicated to empowering consumers with data, inspiration and knowledge around the place they call home, and connecting them with the best local professionals who can help. Zillow serves the full lifecycle of owning and living in a home: buying, selling, renting, financing, remodeling and more. In addition to Zillow.com, Zillow operates the most popular suite of mobile real estate apps, with more than two dozen apps across all major platforms. Launched in 2006, Zillow is owned and operated by Zillow Group, Inc. (NASDAQ:Z and ZG) and headquartered in Seattle.

Zillow, Zestimate and Zillow Prize are registered trademarks of Zillow, Inc.

¹ The competition counties were Los Angeles, Orange, and Ventura counties in California.
²  The error rate is defined as the median absolute percent error.

SOURCE Zillow