Scalable real-time personalized recommendation system
Submitted by Jasvinder Singh (@jasvinder) on Monday, 15 June 2015
This talk goes over some challenges in scaling a real time personalized recommendation system that can dynamically adapt to user actions and incorporate these signals into various applications like search, recommendations, predictive suggestions etc.
E-commerce applications these days are driven by personalization. And to provide these highly personalized user experiences, we need systems that track every user action and dynamically adapts sites’ search navigation and content uniquely to each user. This needs systems of massive scale that can process a large number of user events.
Bloomreach’s SNAP product personalizes site discovery for all consumers on any device or channel in real time to instinctively present the most relevant search results, left-navigation and contextual filters. This real time engine captures each individual user’s behaviour that further can be used to create cross device personalized search and navigation results that deliver true personalization to each user.
Jasvinder and Suchi worked on User data and personalization platform scaling for Bloomreach’s personalization service.
Jasvinder has a B.Tech, Computer Science from IIIT, Allahabad. He worked at Microsoft as a computer scientist for 5 years before joining Bloomreach.
Prior to Bloomreach, Suchi was a founding member of the Android framework team and has made extensive contributions to the Android framework.Suchi has an MS from University of Cincinnati and BE from BITS, Pilani. Her prior work experience includes working in companies like Google, Motorola and IBM Almaden.