Company
eBay
11 cases from eBay (E-commerce, Marketplace, Adtech), each digested from a public talk or engineering post and linked to the original. 7 were checked in an online A/B test; 2 report results in production.
Tasks: Retrieve and rank from millions of items, Recommend to new users and new items, Rank search results, Learn user and item embeddings, Build a data platform and 4 more. Methods: Two-tower model, Gradient boosting, Pairwise ranking, Multimodal embeddings, Approximate nearest neighbors, k-nearest neighbors and 23 more. Tools: BERT, Apache Airflow, ResNet, Apache Spark, CLIP, Apache Hadoop and 11 more.
Tech blog: tech.ebayinc.com
| Evolving Recommendations: A Personalized User-Based Ranking Model | e-commerce | 2023-10 | |
| Beyond Words: How Multimodal Embeddings Elevate eBay's Product Recommendations | marketplace | 2023-09 | |
| eBay’s Blazingly Fast Billion-Scale Vector Similarity Engine | marketplace | 2023-05 | |
| How eBay's New Search Feature Was Inspired By Window Shopping | e-commerce | 2023-03 | |
| Variable Hub: Easier Data Integration for Risk Decisioning | e-commerce | 2023-01 | |
| How eBay Created a Language Model With Three Billion Item Titles | marketplace | 2023-01 | |
| Increase A/B Testing Power by Combining Experiments | e-commerce | 2022-10 | |
| Multi-Objective Ranking for Promoted Auction Items | marketplace | 2022-09 | |
| Multi-Relevance Ranking Model for Similar Item Recommendation | marketplace | 2022-06 | |
| Improving Shopping Recommendations for Customers Through eBay’s Relevance Cascade Model | e-commerce | 2022-04 | |
| Building a Deep Learning Based Retrieval System for Personalized Recommendations | marketplace | 2022-03 |