This week, Zephy McKanna sets out to explain Multi-Armed bandits. Here at Wayfair, we are constantly testing new algorithms, product sort orders, marketing, and other messages using epsilon-first Multi-Armed Bandits – also known as A/B tests. We are also employing some more interesting MAB algorithms, like Thompson Sampling, to dynamically…
In this series, the Global Mobility team in our European HQ speaks to employees about their journey to Wayfair, and what moving overseas entailed for them. We begin with Bernie Miles, who joined Wayfair as Head of Engineering to strengthen technology and innovation for our Berlin-based software teams. He brings…
This week in Wayfair Data Science’s explainer series, Tim O’Connor discusses experimentation in the context of data science. Experiments are crucial to data science, helping to determine which version of a model is to use in future iterations of a system or generating new sources of data unavailable in a…
Becoming a software engineer isn’t always straightforward or the same for each person; careers in the industry can start at any point in your working life, backed by a variety of studied disciplines or work experience. We know that good software engineers don’t always take the traditional path into development,…
Welcome back to Wayfair Data Science’s Explainer Series! This week Afshaan Mazagonwalla will be speaking about Bayesian Machine Learning. Wayfair uses Bayesian and Reinforcement Learning based techniques for balancing the exploration – exploitation trade off between new and popular items in ranking products on the website and for recommending sales…
Find out about how Wayfair tackles product recommendations in our first installment! Wayfair Data Science is composed of a number of sub-teams, each tackling a different set of specific business challenges. In order to give you a taste of the wide array of people and workstreams we have here on…
At Wayfair, we pride ourselves on our speedy response times to issues during heavy web traffic to ensure a smooth customer experience. As we scale and continue adding products to our catalog, it is imperative that our backend infrastructure is able to handle increased traffic, especially during retail peaks and…
Wayfair’s software engineering history demonstrates a common theme throughout its time: It moves fast and is a core trait of our business. To create and support the right foundations, we need our infrastructure to move faster than our ideas, and this is especially true for our hybrid environment objectives in…
At Wayfair, we’re always looking forward and we’re always exploring new and promising technology. Through our partnership with Magic Leap we’ve made some groundbreaking contributions to an emerging computing paradigm – spatial computing. In August, we launched our first experience on Magic Leap One. We created a web experience for…
In September, Wayfair hosted React Boston 2018, two full days of augmented reality demos, beautiful and surprising web animations, DOM-related horror stories (with mostly happy endings), component kits, game shows, Forbidden Planet references, and more, all made possible by ReactJS. This year picked up on several of the themes introduced…
As we head into Black Friday, Cyber Monday, and retail’s peak season for 2018, I wanted to reflect back on some excitement we had earlier in the year at Wayfair; specifically how we reacted and built, as a tech team, toward challenges we hadn’t seen before. I hope other e-commerce…
