Data Science

Wayfair and its subsidiary brands operate globally and we send out millions of marketing emails every day to communicate with our customers. To improve customer satisfaction and increase customer engagement, we have developed a new generation of daily sales email models (Nightingale) to make email sending decisions. The Nightingale model is built via a scalable retraining pipeline to serve different business needs across all regions and brands.

Today, many companies rely heavily on third-party event tracking platforms for collecting event data. Perhaps the most well-known of these is Google Analytics. However, at Wayfair, we chose to go another route, largely eschewing the third-party vendor model to develop our own first-party event tracking platform. It’s called Scribe.

The Time Informed Calibration process extends the capabilities of Wayfair’s customer models by converting raw model output to realistic probabilities and incorporating information on expected trends.

I recently had the honor of speaking at EmTech Digital, MIT Technology Review’s signature conference on artificial intelligence (AI) and business leadership. This isn’t my first time speaking at the conference, but it is my first time doing it in person.

As a technology company, Wayfair encourages all team members to roll up their sleeves and innovate. We take immense pride in how our work impacts customers and contributes to the business’s success. We also derive great satisfaction when a team member is recognized by the larger technology community.

Suppliers are an integral part of Wayfair, and providing them with real-time and high-quality data with flexibility is important for our mission. Today I’m going to highlight two specific areas: how Wayfair is leveraging real-time data to provide suppliers with up-to-date sales information and how our team has tackled some of the problems that emerged along the journey.

Every day, Wayfair customers sift through more than 33 million items. Their goal? To find the perfect items to create a home they love. It’s not a grueling and stressful search, and their success isn’t the result of good luck. It’s the byproduct of a technology team committed to enhancing the customer experience through cutting-edge solutions.

Machine learning (ML) profoundly transformed the digital shopping experience for millions of people worldwide. We’ve seen this at Wayfair, where our teams are continuously delivering intelligent and improved experiences for our customers by integrating ML at every stage of their journey with us. Right now Wayfair is leveraging hundreds of ML applications, which on the outside are improving marketing campaigns, improving the visual merchandising of the products we sell, personalizing product recommendations, enabling high-quality customer service, and more.

I’m excited to share that today INFORMS announced Wayfair received the 2022 INFORMS Prize, which recognizes businesses for their “sustained and enduring achievement and success of utilizing Operations Research (O.R.) and analytics into our organizational decision making.”

When customers submit search queries, such as “ivory jute oriental,” it is essential for the search engine to understand which types of products they are looking for. In this case, the customer is likely shopping for an area rug. Equipped with this knowledge, we can tailor the search results page by displaying area rug-specific filters and banners and refine the search results by first showing area rugs. At Wayfair Search, the Query Classifier Model performs this task of real-time prediction of the desired product types based on user search queries. This blog post discusses how we designed, trained, and deployed this deep learning classification model at SearchTech.

Customers’ tastes may change over a period of time. How can we leverage their browse history to make sure our recommendations reflect their most up-to-date preferences?

How Wayfair optimizes content placement considering competing short term marketing and long term business goals