Communications of the ACM
Winners Announced for the Zillow Prize
A three-person team won the $1-million grand prize in the Zillow Prize competition by out-forecasting Zillow's own predictive Zestimates.
Credit: iStockPhoto
The Zillow Prize competition pitted nearly 4,000 teams against one another in an effort to develop a computerized system that could predict the future sale price of homes.
Zillow, a real estate company, hopes to use what it learned from these teams to improve its own system of predicting home prices, called the "Zestimate."
The winning team, which received the $1-million grand prize, consisted of Chahhou Mohamed of Morocco, Jordan Meyer of the U.S., and Nima Shahbazi of Canada, whose predictions bettered the Zestimate by about 13%.
The winning team combined various models in an ensemble approach, and put considerable effort into the ancillary data they fed into some of their models, including the home's proximity to bodies of water, and the prevailing level of road noise. Real estate data such as square footage, the number of bedrooms, and the sale prices of comparably sized homes in the area also was fed to the algorithm.
From IEEE Spectrum
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found