I was Director of Engineering, Data Science and Machine Learning at Etsy Inc. during 2016 and 2020. My responsibilities included:
- As a manager, I grew an organization of multiple teams from 5 to almost 40 Master and Ph.D. level Data Scientists and Machine Learning Engineers, located in New York City and San Francisco offices, with backgrounds in Computer Science, Operation Research, Electrical Engineering, Statistics, Economics, Physics and others, including graduates from Harvard University, Cornell University, Carnegie Mellon University and others. My reports include several front-line managers and one architect, both grown internally and hired externally.
- As a department head, I worked with senior leaders in the company (e.g., VP of Engineering, CTO and others) to develop strategies for cross-functional collaboration to incorporate Machine Learning as a key element in product development, complementing Design, Analytics, UX Research, and Product Engineering.
- As a technical leader, I drove Machine Learning and Data Science vision and deliver cutting-edge scientific solutions for Search & Discovery, Personalization & Recommendation and Computational Advertising by utilizing a wide range of technologies such as deep learning, probabilistic modeling, image understanding (computer vision), user profiling, query understanding, text mining and others. Results are published in SIGIR 2018, WSDM 2019, KDD 2019, WSDM 2020 and other venues.
We worked on innovations to power products and develop state-of-the-art algorithms and models. We involved in research communities by giving talks and publish high-quality papers in top computer science venues. Check out our blog posts about how data science can directly impact our products.
Talks
- L. Hong. “Search for E-Commerce: (Not) Solved (Yet)” at The 2018 SIGIR Workshop On eCommerce, Ann Arbor, Michigan, July 2018. [Slides]
- L. Hong. “AI for Search in E-Commerce“ at AICon 2018, Beijing, China, Jan 2018. [Slides]
- L. Hong. “AI in E-Commerce at Etsy” at Insights Data Science, New York City, NY, August 2017. [Slides]
- L. Hong. “AI in E-Commerce at Etsy” at Machine Learning Summit, Beijing, China, June 2017. [Slides]
- L. Hong. “Data Science at Etsy” at Department of Statistics at Columbia University, New York, NY, Dec. 2016.
- K. Aryafar. “Machine Learning as the Key to Personalized Curation” at AirBnB’s OpenAir Tech Talks, August, 2015.
Blog Posts
- N. Subedi. Modeling User Journeys via Semantic Embeddings. July, 2018.
- M. Nayyar. Modeling Spelling Correction for Search at Etsy. May, 2017.
- G. Fernandez-Kincade. Targeting Broad Queries in Search. July, 2015.
- F. Condon. How Etsy Uses Thermodynamics to Help You Search for “Geeky”. August, 2015.
- R. Hall. Personalized Recommendations at Etsy. November, 2014.
- J. Attenberg. Conjecture: Scalable Machine Learning in Hadoop with Scalding. June, 2014.
Publications
- X. Yin and L. Hong. The Identification and Estimation of Direct and Indirect Effects in A/B Tests through Causal Mediation Analysis. In KDD 2019.
- H. Jiang, A. Sabharwal, A. Henderson, D. Hu and L. Hong. Understanding the Role of Style in E-commerce Shopping. In KDD 2019.
- A. Stanton, A. Ananthram, C. Su and L. Hong. Revenue, Relevance, Arbitrage and More: Joint Optimization Framework for Search Experiences in Two-Sided Marketplaces. ArXiv. 2019.
- X. Zhao, R. Louca, D. Hu and L. Hong. Learning Item-Interaction Embeddings for User Recommendations. DAPA at WSDM 2019.
- N. Ju, D. Hu, A. Henderson and L. Hong. A Sequential Test for Selecting the Better Variant – Online A/B testing, Adaptive Allocation, and Continuous Monitoring. In WSDM 2019.
- D. Hu, R. Louca, L. Hong and J. McAuley. Learning Within-Session Budgets from Browsing Trajectories. In RecSys 2018.
- L. Wu, D. Hu, L. Hong and H. Liu. Turning Clicks into Purchases: Revenue Optimization for Product Search in E-Commerce. In SIGIR 2018.
- A. Stanton, L. Hong and M. Rajashekhar. Buzzsaw: A System for High Speed Feature Engineering. In SysML 2018.
- K. Aryafar, D. Guillory and L. Hong. An Ensemble-based Approach to Click-Through Rate Prediction for Promoted Listings at Etsy. In AdKDD & TargetAd 2017 workshop, held in conjunction KDD 2017.
- C. Lynch, K. Aryafar, and J. Attenberg. Images Don’t Lie: Transferring Deep Visual Semantic Features to Large-Scale Multimodal Learning to Rank. In KDD 2016. 541-548.
- S. Zakrewsky, K. Aryafar and A. Shokoufandeh. Item Popularity Prediction in E-commerce Using Image Quality Feature Vectors. CoRRabs/1605.03663 (2016).
- R. Hall and J. Attenberg. Fast and Accurate Maximum Inner Product Recommendations on Map-Reduce. In WWW (Companion Volume) 2015. 1263-1268.
- D. Hu and T. Schneiter. Targeted Content for a Real-Time Activity Feed: For First Time Visitors to Power Users. In WWW (Companion Volume) 2015. 1269-1274.
- D. Hu, R. Hall and J. Attenberg. Style in the long tail: discovering unique interests with latent variable models in large scale social E-commerce. In KDD 2014. 1640-1649. (Best Industrial Paper Award)
- K. Aryafar, C. Lynch and J. Attenberg. Exploring User Behaviour on Etsy through Dominant Colors. In ICPR 2014. 1437-1442.