Data Science

Find out about how Wayfair tackles product recommendations in our first installment!

So, you graduated college, spent half a decade in a quantitative PhD program, maybe took a postdoctoral fellowship….and now what? You may want to stay the course and pursue a tenure track faculty position at a university–or, you may not. While the pressure to remain within the academy post PhD can at times feel overwhelming, if you’re in the latter group and are considering making the switch from academia to industry, know that you’re not alone.

Uplift models seek to predict the incremental value attained in response to a treatment. For example, if we want to know the value of showing an advertisement to someone, typical response models will only tell us that a person is likely to purchase after being given an advertisement, though they may have been likely to purchase already. Uplift models will predict how much more likely they are to purchase after being shown the ad. The most scalable uplift modeling packages to date are theoretically rigorous, but, in practice, they can be prohibitively slow. We have written a Python package, pylift, that implements a transformative method wrapped around scikit-learn to allow for (1) quick implementation of uplift, (2) rigorous uplift evaluation, and (3) an extensible python-based framework for future uplift method implementations.

Search is critical to the customer experience at Wayfair. What we show on the first page of results is incredibly important for users. The graph below shows what many people might already know when it comes to browsing and search habits: The majority of customers rarely look beyond the products on the first page of search results.

Workplace diversity is not just an ethical issue. Teams that overcome diversity issues (e.g., gender, race, ethnicity, experience) often achieve greater productivity than homogeneous teams. If you’re surrounded by people who are different from you, you will be constantly challenged to reexamine facts, think deeper, and explain better. In this way diversity can enhance creativity and boost team performance and technological innovation.

Top left to right: Yumeng Ma (University of Michigan), Steven Yin (Columbia), Michael Spece, Carnegie Mellon University), Quinn Donahoe (University of Pittsburgh), Cristian Gavrus (UC Berkeley)

No two people's paths to Wayfair are exactly the same. On our data science team alone we employ physicists, neuroscientists, biophysical chemists, economists, mathematicians, statisticians, and more! Our data scientists are united by a love of data and a knack for problem solving, but each person has a different story to tell about how they gained these skills.

Last year, Wayfair launched Visual Search, a new and novel way to find products on our website. Users can now upload photos of furniture they like and find visually similar matches in an instant. If you need a little refresher on this technology, the original blog post can be found here.

Since I began my tenure at Wayfair as a data scientist, many PhD students and postdocs have reached out to ask for advice about the transition to data science in industry. After a fruitful collection of conversations, I’ve realized that there are popular misconceptions about what it means to be a data scientist.

As data scientists, we face a variety of problem types. One of our critical challenges is identifying the proper methodological approach to solve each problem. By doing this, we avoid force-fitting the wrong tool to solve a problem, and we avoid having to reformulate a question to fit a specific method.

Right now, Wayfair has about 86,000 rugs available for purchase. On the first page of our rug category page, however, we only have room for the top 48. You see even fewer if you don’t happen to scroll or swipe down. When it comes to our customer’s experience, what we choose to place at the top makes a big difference! At present, we don’t explicitly showcase a diverse array of products. On browse pages for categories such as rugs, couches, or coffee tables, we instead combine personalized recommendations with the general popularity of products.

Wayfair offers a zillion things home, with one of the world's largest online selections of furniture, home furnishings, décor and goods, including more than eight million products from over 10,000 suppliers. Wayfair's expanding Visual Search team is leveraging deep learning and our expansive catalog of images to create an exciting new way for shoppers to find the perfect product for their homes.