Some challenges with Recommender Systems at LinkedIn (via Zoom)

Abstract: Machine Learning based recommender systems power almost every aspect of the LinkedIn experience. I will discuss three challenging and practical problems that we have made a dent at. With the LinkedIn feed as the main example, I’ll describe how we increased productivity of engineers through optimization techniques, improved experimentation methods in networks, and how we are measuring and mitigating bias in our algorithms. 

Bio:  Souvik Ghosh is a Director of Engineering at LinkedIn, leading the AI applied research team, a team of scientists and engineers who develop core AI models and algorithms that power applications across LinkedIn like the feed, notifications, ads, jobs and learning. Souvik obtained his PhD in applied probability from Cornell University and prior to joining LinkedIn, Souvik held the roles of Research Scientist at Yahoo! Research and Assistant Professor of Statistics at Columbia University. Souvik has an extensive experience in research and development of recommender systems and related fields, many publications and patents and he regularly serves in the program committees of conferences like KDD, ICML, NeurIPS and CIKM.