The Browsemaps: Collaborative Filtering at LinkedIn
Lili Wu, Sam Shah, Sean Choi, Mitul Tiwari, Christian Posse · 2014
Many web properties make extensive use of item-based collabora-tive filtering, which showcases relationships between pairs of items based on the wisdom of the crowd, for navigational aids and recom-mendation systems. This paper presents LinkedIn’s collaborative filtering infrastructure, known as Browsemaps. A key characteristic of our solution is that rapid development, deployment, and compu-tation of collaborative filtering is possible for almost any use case through a simple domain specific language with scaling and other operational issues handled by the system. As part of this work, we also present case studies on how this platform is used at LinkedIn in various recommendation products, as well as lessons learned in the field over the several years this system has been in production. 1.