Spotify Ab

Zahra Nazari

Johan Pages

Christophe Charbuillet

Clay Gibson

Mounia Lalmas-Roelleke

Benjamin Austin Carterette

Alexander Zachary Gain

Himan Abdollahpouri

Tony Jebara

Maria Dimakopoulou

A method includes displaying, at a device of a first user, a user interface that includes: representations of content items of a first content domain that the first user has consumed; and an affordance for viewing recommended content items of a second content domain, distinct from the first content domain. The method includes obtaining, for each respective content item of a plurality of content items of the second content domain, consumed by at least one user other than the first user, information for the respective content item, and determining a first content item of the plurality of content items. The method includes, in response to a user input selecting the affordance for viewing the recommended content items of the second content domain, displaying at the device of the first user, information that corresponds to the first content item of the plurality of content items of the second content domain.

Systems and methods for providing content based on consumption in a distinct domain

An electronic system stores metadata for a plurality of media items, including, for each media item of the plurality of media items, at least one categorical identifier from a set of categorical identifiers. For a user of the media-providing service, the electronic system (i) determines a distribution of interests of the user with respect to the set of categorical identifiers; (ii) generates a network graph configured to represent a calibrated media item selection task, wherein the network graph represents respective relevance scores for each respective media item of the plurality of media items and the distribution of interests of the user with respect to the categorical identifiers; (iii) selects a set of media items from the plurality of media items to recommend to the user by solving for a maximum flow of the network graph; and (iv) provides the set of media items as recommendations to the user.

Systems and methods for calibrating recommendations using a maximum flow approach

A server obtains user data for a respective user, including data corresponding to the respective user's consumption of media in a first content domain. Before obtaining, for the respective user, data corresponding to a second content domain, the server uses a neural network to generate a user embedding for the respective user based on the user data. The server generates, for a plurality of content items of the second content domain consumed by users other than the respective user, a respective content item embedding. The respective content item embedding is based on user embeddings of the at least one user other than the respective user. The server system determines, using the user embedding for the respective user and respective content item embeddings, a first content item in the second content domain that meets matching criteria for the respective user and provides the first content item to the respective user.

A server obtains user data corresponding to a first content domain. The server identifies, from the user data, a plurality of labels. A respective label of the plurality of labels corresponds to a distinct characteristic of content items of the first content domain. The server utilizes a neural network to generate a plurality of user embeddings. A respective user embedding of the plurality of user embeddings includes a plurality of labels that correspond to a respective user. The server determines, using the plurality of user embeddings, a first content item of a plurality of content items of a second type that meets matching criteria for a first user. The server further provides, to a device of the first user, information that corresponds to the first content item of the second content domain.

Growing community of inventors

New York, NY, United States of America

Zahra Nazari