Etsy’s Data Science & Machine Learning (DSML) organization is comprised of talented engineers and scientists with diverse backgrounds.

Together, we tackle challenging problems in Machine Learning, Statistics, and Large-Scale Systems, to improve the lives of millions of buyers and sellers on Etsy around the world.

Publications

The DSML org at Etsy stays involved in the research community in order to stay ahead of the technology curve. Check out our recent papers to see what we’ve been working on. A full list of publications can found on our publications page.

Featured
2020
Causal Meta-Mediation Analysis: Inferring Dose-Response Function From Summary Statistics of Many Randomized Experiments
2020

It is common in the internet industry to use offline-developed algorithms to power online products that contribute to the success of a business. Offline-developed algorithms are guided by offline evaluation metrics, which are often different from online business key performance indicators (KPIs). To maximize business KPIs, it is important to pick a north star among all available offline evaluation metrics. By noting that online products can be measured by online evaluation metrics, the online counterparts of offline evaluation metrics, we decompose the problem into two parts. As the offline A/B test literature works out the first part: counterfactual estimators of offline evaluation metrics that move the same way as their online counterparts, we focus on the second part: causal effects of online evaluation metrics on business KPIs.

Read More →
2020
2020
Debiasing Grid-based Product Search in E-commerce
2020

The widespread usage of e-commerce websites in daily life and the resulting wealth of implicit feedback data form the foundation for systems that train and test e-commerce search ranking algorithms. We aim to utilize all types of implicit feedback as the supervision signals. In this work, we extend unbiased learning to rank to the world of e-commerce search via considering a grid-based product search scenario. We propose a novel framework which (1) forms the theoretical foundations to allow multiple types of implicit feedback in unbiased learning to rank and (2) incorporates the row skipping and slower decay click models to capture unique user behavior patterns in grid-based product search for inverse propensity scoring.

Read More →
2020
2021
Interpretable Attribute-based Action-aware Bandits for Within-Session Personalization in E-commerce
2021

When shopping online, buyers often express and refine their purchase preferences by exploring different items in the product catalog based on varying attributes, such as color, size, shape, and material. As such, it is increasingly important for e-commerce ranking systems to quickly learn a buyer’s fine-grained preferences and re- rank items based on their most recent activity within the session. In this paper, we propose an 𝑂nline 𝑃ersonalized 𝐴ttribute-based 𝑅e-ranker (OPAR), a light-weight, within-session personalization approach using multi-arm bandits (MAB). By representing each arm in the MAB as an attribute, we reduce the complexity space while offering more fine-grained personalization.

Read More →
2021

Projects

Our work on the DSML teams span across many product applications including Recommendations, Personalization, Search, Computer Vision, Advertising, and Marketplace Economics.

Learn more about our projects below. (Coming Soon!)

Careers

We are currently hiring!

If you’re interested in working with us, check out our current openings in DSML below. To see more job openings at Etsy, visit our Careers Page, in the Data Science & Machine Learning Sub Department under the Engineering.