SpectroBrain: Detecting Phone Spam with Semi-Supervised Learning
Zillow » Tech
by Winston Quock
1y ago
At Zillow Rentals, we cherish the trust and safety of our users with the utmost priority. While renters seeking their next dream home are communicating with property owners/managers using our platform’s email and phone messaging features, spammers also are interested in these same communication channels. For example, spammers have called our users to pitch tax debt relief services or cryptocurrency investments. We must proactively identify and block these unwanted  callers. Zillow Rentals has developed many sophisticated tools to detect and fend off spammers. One such tool uses machine le ..read more
Visit website
The Data Infra Behind Zillow’s 3x Growth in Experiment Volume
Zillow » Tech
by Aaron Wroblewski
1y ago
Introduction ZEXP: AB Testing for all of Zillow (Zall) When I was tapped to lead a newly formed team at Zillow focused on experimentation in mid-2020, Zillow was already one of the most visited real estate brands, with nearly 200 million monthly unique users. We had a clear need to continue to innovate our product to help our customers do more than browse homes and connect with real-estate agents, enabling them to “unlock life’s next chapter”. A company positioning itself to lead Real Estate 2.0 needed a rapidly accelerating innovation engine. Today the mission & vision of the Zillow Exper ..read more
Visit website
Building the Neural Zestimate
Zillow » Tech
by Eric Ringger
1y ago
Zillow’s signature home valuation tool — the Zestimate — is a powerful starting point in determining a home’s value. Since its launch in February 2006, the Zestimate has evolved from providing 40 million homes with an estimated home value updated monthly to covering more than 100 million homes in the U.S. with estimates that react to market trends several times a week, all while improving the accuracy of the estimates themselves. The evolution of the Zestimate has been enabled by transformative advances in machine learning and artificial intelligence over the past decade. In June 2021, we laun ..read more
Visit website
Helping Users Discover Their Dream Homes Through Home Insights Collections
Zillow » Tech
by Giuliano Janson
1y ago
Figure 1: Home Insights Collections are lists of thematically coherent home recommendations featuring highly relevant aspects of homes such as pools, views, remodeled kitchens, open floor plans and many others.   At Zillow Group, we strive to delight each and every user with the most personalized home discovery experience. Some users might focus their search on the number of bedrooms, square footage, or location. Others might dream of that newly remodeled kitchen with quartz countertops and a chef stove, or a large patio area to entertain friends and cook amazing barbecue.  In this ..read more
Visit website
How Zillow Data Science Measures Business Outcomes with Bayesian Statistics
Zillow » Tech
by Matt DiNauta
1y ago
In the Transaction & Engagement Analytics team at Zillow, our mission is to use data to uncover new strategic directions and optimize ongoing initiatives. We are the owners and stewards of metrics around customer interactions, including connections, when a home buyer or seller is connected with a real estate professional through Zillow, and transactions, when an individual goes on to buy or sell a home with the real estate professional they connected with through Zillow. We are often interested in the transaction rate, or the proportion of all interactions between consumers and agents begi ..read more
Visit website
Serving Machine Learning Models Efficiently at Scale at Zillow
Zillow » Tech
by Peilun Li
1y ago
Zillow was founded with a goal of “turning on the lights” for consumers, and it continues as a core value of the company today. Our mission is to give people the power to unlock life’s next chapter and help them find, make a winning offer on, and purchase their next home through low-friction digital solutions.  This includes putting an estimate of a home’s market value — called the Zestimate® — on every rooftop, giving people the power to make informed decisions about one of the most important transactions of their lifetime. Many Zillow features[1] are powered by data and machine lea ..read more
Visit website
Identifying High-Intent Buyers
Zillow » Tech
by Ondrej Linda
1y ago
The Zillow® website is visited monthly by tens of millions of customers. Some arrive after typing a home address into a search engine. Others might be frequent and highly engaged users with the Zillow app installed on their phone, keeping an eye on new listings in their desired location. Some are renting and dreaming about buying. Many are happy with their current home and are only interested in understanding the value of their property or that of their friends and neighbors via the Zestimate® tool. Others are on Zillow to find the right agent, tour a home, or even to secure financing via Zill ..read more
Visit website
Incorporating Listing Descriptions into the Zestimate
Zillow » Tech
by Emily Gill
1y ago
Figure 1: A Zillow Home Details Page (HDP) with a detailed listing description and blue Home Insight tags below.   “Freshly painted and immaculately clean. Easy to move right in and enjoy the neighborhood. Newer Roof, Appliances, HVAC, A/C and Garage. Open and bright floorplan. Covered front porch overlooks raised garden beds. Private backyard with a Trex Deck, Paver Stone Patio, and easy to maintain lawn. Large family room with fireplace in the lower level. Private small non-conforming bedroom is good for day sleepers/ night shift workers. Basement level also includes Laundry room, Off ..read more
Visit website
Optimizing Elasticsearch for Low Latency, Real-Time Recommendations 
Zillow » Tech
by Kelsey Juraschka
1y ago
At Zillow, we incorporate personalized recommendations in many product areas to improve the user experience. The recommendations are incorporated into search results, Home Detail Page recommendation modules, and personalized collections, such as on the mobile updates tab.  These APIs must be low latency so that page load time is not impacted. Previously, we relied heavily on batch systems to provide recommendations for experiences other than personalized search results. This year, we have focused on generating most of our recommendations in real-time. Generating recommendations in real ti ..read more
Visit website
Helping Home Shoppers Find a Home to Love Through Home Insights
Zillow » Tech
by Anish Khazane
1y ago
When searching for a home, it all starts with the search function. Based on search criteria and filters, users are presented with a list of ranked homes that meet their needs.  Even then, browsing dozens or even hundreds of homes to find the right one feels daunting. Most home descriptions look similar, and in high inventory zipcodes it can be hard to remember what was unique about Home A versus Home B.  Zillow is working to solve this problem in many ways. One way is through Home Insights.  The Home Insights pipeline extracts, filters, ranks and displays interesting terms from ..read more
Visit website

Follow Zillow » Tech on FeedSpot

Continue with Google
Continue with Apple
OR