Abstract: Described herein are techniques for processing content items for presentation via a content feed of an online service. Upon receiving a request associated with a particular end-user of an online service for a content feed, a connection graph is analyzed to identify a plurality of content items that are eligible for presentation to the end-user. Some subset of content items that share a common relationship with the end-user, as indicated by a common edge in the connection graph, are identified. This subset of content items is then grouped together for presentation within the content feed in a content carousel, where the content carousel is positioned within the content feed, relative to other content items, based on the highest ranking content item presented via the content carousel.

Abstract: Techniques for personalizing a user experience for a user of an online service using machine learning are disclosed herein. In some embodiments, a computer system detects a first request by a first computing device of a first user to access content of an online service, identifies at least one content item to display based on the first request, and selects a first presentation template from amongst a plurality of presentation templates based on the at least one content item and an identification of the first user. In some example embodiments, the plurality of presentation templates is stored in a database of the online service, and each one of the plurality of presentation templates is distinct from one another and defines a corresponding manner in which to display the at least one content item.