Mitul.Tiwari

Mitul Tiwari

Staff Engineer; Search, Network and Analytics; LinkedIn

Mitul Tiwari is a Staff Research Engineer and Tech Lead at Search, Network, and Analytics group at LinkedIn. He has been working on large-scale social recommender systems such as “People You May Know” and “Related Searches”. His interests include recommender systems, social network analysis, large-scale data mining, machine learning, and distributed systems. Previously, he worked at Kosmix (now Walmart Labs) as a Lead Member of Technical Staff, where he worked on web-scale document and query categorization, and its application to vertical search, topic pages, and tweets classification. He completed his PhD in Computer Science from the University of Texas at Austin. Earlier he received his under graduation from Indian Institute of Technology, Bombay. He has co-authored more than a dozen publications in conferences such as WWW, VLDB, CIKM, and SPAA. You can follow @mitultiwari on Twitter and find more details here: http://www.mitultiwari.net

Large-Scale Social Recommender Systems at LinkedIn
Track: Applied Machine Learning and Data Science

Location:
Bayview A/B

Abstract:
Recommender Systems are very important for social networks such as LinkedIn for engaging users, discovering new content, connections, opportunities, and satisfying users needs. This talk gives an overview of various analytics products at LinkedIn such as Jobs recommendations, Skills endorsements, People You May Know, and LinkedIn Today. Each of these products can be viewed as a large scale social recommendation problem, which analyzes billions of possible options, and suggests appropriate recommendations.

This talk will also touch upon various big data technologies such as Hadoop MapReduce, Azkaban work-flow management, Voldemort key-value store, and Kafka publish-subscribe system, to process terabytes of data for building large-scale social recommendation systems. Overall, people interested in building interesting social data products using machine learning and big data technologies will greatly benefit from this talk.