Real estate information & home-related marketplace site Zillow recently announced that it was fine-tuning its Zestimate algorithm to boost accuracy and improve its median error rate from 8% to 6%. Zestimates are published 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 their Zestimate, Zillow uses data from county & tax assessor records as well as direct feeds from hundreds of multiple listing services and brokerages.
“Since we launched the Zestimate 10 years ago, we have been continually working on making it even better. With the additional statistical models and computing power behind today’s update, we are able to provide consumers even better information about millions of homes, equipping them to make informed decisions when talking with a real estate profession about buying or selling.” said Stan Humphries, Zillow Group chief analytics officer and creator of the Zestimate.
Click here to read the full release on Zillow.com.
Click here to download a spreadsheet about the Zestimate’s data coverage and accuracy.