An Industrial-Scale Sequential Recommender for LinkedIn Feed Ranking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hertel, Lars, Srivastava, Gaurav, Naqvi, Syed Ali, Kumar, Satyam, Zhang, Yue, Ocejo, Borja, Zelditch, Benjamin, Englhardt, Adrian, Cheng, Hailing, Hu, Andy, Alonso, Antonio, Li, Daming, Dangi, Siddharth, Zhu, Chen, Zhou, Mingzhou, Li, Wanning, Huang, Tao, Borisyuk, Fedor, Parameswaran, Ganesh, Tiwana, Birjodh Singh, Sankar, Sriram, Lan, Qing, Choi, Julie, Ghosh, Souvik
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918532023844864
author Hertel, Lars
Srivastava, Gaurav
Naqvi, Syed Ali
Kumar, Satyam
Zhang, Yue
Ocejo, Borja
Zelditch, Benjamin
Englhardt, Adrian
Cheng, Hailing
Hu, Andy
Alonso, Antonio
Li, Daming
Dangi, Siddharth
Zhu, Chen
Zhou, Mingzhou
Li, Wanning
Huang, Tao
Borisyuk, Fedor
Parameswaran, Ganesh
Tiwana, Birjodh Singh
Sankar, Sriram
Lan, Qing
Choi, Julie
Ghosh, Souvik
author_facet Hertel, Lars
Srivastava, Gaurav
Naqvi, Syed Ali
Kumar, Satyam
Zhang, Yue
Ocejo, Borja
Zelditch, Benjamin
Englhardt, Adrian
Cheng, Hailing
Hu, Andy
Alonso, Antonio
Li, Daming
Dangi, Siddharth
Zhu, Chen
Zhou, Mingzhou
Li, Wanning
Huang, Tao
Borisyuk, Fedor
Parameswaran, Ganesh
Tiwana, Birjodh Singh
Sankar, Sriram
Lan, Qing
Choi, Julie
Ghosh, Souvik
contents LinkedIn Feed enables professionals worldwide to discover relevant content, build connections, and share knowledge at scale. We present Feed Sequential Recommender (Feed SR), a transformer-based sequential ranking model for LinkedIn Feed that replaces a DCNv2-based ranker and meets strict production constraints. We detail the modeling choices, training techniques, and serving optimizations that enable deployment at a scale of 1.2 billion members. Feed SR has been serving the majority of LinkedIn's Feed traffic for over three months and shows significant improvements in member engagement (+2.10% time spent, +3.52% like, comments, or reshares) in online A/B tests compared to the existing production model. We also describe our deployment experience with alternative sequential and LLM-based ranking architectures and why Feed SR provided the best combination of online metrics and production efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12354
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An Industrial-Scale Sequential Recommender for LinkedIn Feed Ranking
Hertel, Lars
Srivastava, Gaurav
Naqvi, Syed Ali
Kumar, Satyam
Zhang, Yue
Ocejo, Borja
Zelditch, Benjamin
Englhardt, Adrian
Cheng, Hailing
Hu, Andy
Alonso, Antonio
Li, Daming
Dangi, Siddharth
Zhu, Chen
Zhou, Mingzhou
Li, Wanning
Huang, Tao
Borisyuk, Fedor
Parameswaran, Ganesh
Tiwana, Birjodh Singh
Sankar, Sriram
Lan, Qing
Choi, Julie
Ghosh, Souvik
Information Retrieval
LinkedIn Feed enables professionals worldwide to discover relevant content, build connections, and share knowledge at scale. We present Feed Sequential Recommender (Feed SR), a transformer-based sequential ranking model for LinkedIn Feed that replaces a DCNv2-based ranker and meets strict production constraints. We detail the modeling choices, training techniques, and serving optimizations that enable deployment at a scale of 1.2 billion members. Feed SR has been serving the majority of LinkedIn's Feed traffic for over three months and shows significant improvements in member engagement (+2.10% time spent, +3.52% like, comments, or reshares) in online A/B tests compared to the existing production model. We also describe our deployment experience with alternative sequential and LLM-based ranking architectures and why Feed SR provided the best combination of online metrics and production efficiency.
title An Industrial-Scale Sequential Recommender for LinkedIn Feed Ranking
topic Information Retrieval
url https://arxiv.org/abs/2602.12354