What We Do
We create model driven experiments to drive business impact. Check out our blog to learn about ongoing projects!
Terabytes of Data Captured Daily
Billion Google Ads per Month
Full Years of Clickstream Data
Million Tagged and Classified Images
Million Products in Catalogue
Million Customer Reviews
Personalization & Recommendations
ML Systems Engineering
Data Science EU
ReCNet: Deep Learning based Cross-class Recommendations at Wayfair
December 12, 2019
Introduction The main objective of our recommender systems is to narrow down Wayfair’s vast catalogue to assist customers in finding exactly the products they want. Most recommendation algorithms leverage a customer’s browsing history, which inc...
BERT Does Business: Implementing the BERT Model for Natural Language Processing at Wayfair
November 27, 2019
Introduction Every day, Wayfair receives tens of thousands of messages from customers, telling us about their experiences with our products and services through the likes of product reviews, return comments, and various surveys. Considering that our...
Who We Are
We are a diverse group of analytical problem solvers. And we might be more than a little nerdy.
Director of Data Science
University of Chicago
Head of Pricing
Head of DS Merchandising
PhD Operations Research
Head of DS Marketing
MBA Finance & Entrepreneurship
Head of Personalization & Recommendations
Head of Computer Vision
PhD Electrical Engineering
Head of Operations Research
MS Operations Research
Head of ML Systems Engineering
MBA Marketing & E-Commerce
University of Rochester
Head of Data Science EU
Humboldt University of Berlin
How We Work
Here at Wayfair Data Science, our core values are rigor, curiosity, and fun.
From search engines to shipping logistics, Data Science is central to everything we do at Wayfair. As such, it's vital that we get things right. Our thorough in-house testing platform, rolling code deployments, and iterative research-style approach ensure that our work is thorough, precise, and driving the business.
Wayfair’s abundance of data means that there are always new problems to be solved. As such, team members are empowered to explore our data to develop new, high impact ideas and then develop experiments to probe those questions. We also partner with professors and students from Harvard, MIT, Stanford, Columbia, and Cornell to bring the most advanced ML technologies into production.
No one is too busy to brainstorm or answer a question, and code is shared as freely as the snacks in the kitchen. We like doing things together, whether that means collaborating on a pricing experiment or going rockclimbing, kayaking, painting, or visiting a distillery with our coworkers during our monthly pod outings.