TY - GEN
T1 - Personalized Interest Graphs for Theme-Driven User Behavior
AU - Zinman, Oded
AU - Chowdhury, Nazmul
AU - Fiaschetti, Leandro
AU - Brovman, Yuri M.
AU - Feigenblat, Guy
AU - Eshel, Yotam
N1 - Publisher Copyright:
© 2025 Copyright held by the owner/author(s).
PY - 2025/8/7
Y1 - 2025/8/7
N2 - Many eBay users turn to our platform to pursue theme-centric interests that span diverse product categories - for example, a Star Wars fan might search for related video games, toys, memorabilia, and artwork. Existing recommendation systems, typically optimized for short-term engagement, often fail to surface cross-category items aligned with these deeper interests. We present an end-to-end recommendation framework built around a user-interest graph generated by LLM chain. The graph captures user preferences at multiple levels of granularity, enabling a balance between relevance-driven and serendipity-driven recommendations. The system has been deployed at scale, serving millions of users across billions of items. An online A/B test on the eBay homepage showed a significant improvement in engagement with previously unseen categories, alongside gains in purchases and buyer count.
AB - Many eBay users turn to our platform to pursue theme-centric interests that span diverse product categories - for example, a Star Wars fan might search for related video games, toys, memorabilia, and artwork. Existing recommendation systems, typically optimized for short-term engagement, often fail to surface cross-category items aligned with these deeper interests. We present an end-to-end recommendation framework built around a user-interest graph generated by LLM chain. The graph captures user preferences at multiple levels of granularity, enabling a balance between relevance-driven and serendipity-driven recommendations. The system has been deployed at scale, serving millions of users across billions of items. An online A/B test on the eBay homepage showed a significant improvement in engagement with previously unseen categories, alongside gains in purchases and buyer count.
KW - Knowledge Graph
KW - Large Language Models
KW - Recommendation
UR - https://www.scopus.com/pages/publications/105019645323
U2 - 10.1145/3705328.3748133
DO - 10.1145/3705328.3748133
M3 - Conference contribution
AN - SCOPUS:105019645323
T3 - RecSys2025 - Proceedings of the 19th ACM Conference on Recommender Systems
SP - 1038
EP - 1041
BT - RecSys2025 - Proceedings of the 19th ACM Conference on Recommender Systems
PB - Association for Computing Machinery, Inc
T2 - 19th ACM Conference on Recommender Systems, RecSys 2025
Y2 - 22 September 2025 through 26 September 2025
ER -