Online Program Home
My Program

Abstract Details

Activity Number: 65 - New-Generation Experimental Design and Causal Inference in High-Tech Companies
Type: Topic Contributed
Date/Time: Sunday, July 29, 2018 : 4:00 PM to 5:50 PM
Sponsor: Quality and Productivity Section
Abstract #330976 Presentation 1 Presentation 2
Title: LinkedIn Feed Optimization
Author(s): Souvik Ghosh*
Companies: LinkedIn
Keywords: social network; news feed; ranking; network experiments
Abstract:

LinkedIn is the world's largest professional network with more than 500M members. The LinkedIn Feed is a central place where members visit to stay updated with their connections, read news articles, discover career opportunities and many more. Members can take various actions on the feed including 'like', 'share' or 'comment' on an article, apply for a job or watch a video. The actions of a member on a content provides value to the network of the member and the content creator. The member's actions also influences the future behavior of the member. How we rank the various content on the feed influences the interactions of the member and has the ability of shaping the network. We discuss our feed ranking algorithms that optimize value for the network. We also discuss the experiments we run and how we measure the impact of our algorithms.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program