Spotify Ab

David Saverio Susi

Raj Kumar Rajendran

Aron Patrick Glennon

Jiming Shi

Lan Xu

Yi Yuan

Yin Kwan Chung

Aarshay Jain

Shana Offen

Gautham Padmanabhan Nair

Zachary A Pustejovsky

Zachary W Nichols

Jeremiah M Cohen

A server determines, at a first predetermined time, a default decision as to whether to provide a first media content clip after the end of a first media content item. At a second predetermined time, after the first predetermined time, the server initiates a determination of a first decision as to whether to provide the first media content clip after the end of the first media content item. In accordance with the first decision being reached within a predetermined latency period, the server provides the first media content clip to the first electronic device in accordance with the first decision. In accordance with a determination that the predetermined latency period has elapsed without the first decision being reached, provides the first media content clip to the first electronic device in accordance with the default decision.

Systems and methods for dynamic media content streaming

A method performed at a server system includes providing to a device a media content item included in a listening session. The method includes receiving from the device characteristics of the listening session corresponding to a first time and determining, based on the characteristics, a default decision as to whether to provide a media content clip after the media item. The method includes receiving characteristics of the listening session corresponding to a second time and initiating a determination of a first decision as to whether to provide the media content clip after the media item. In accordance with the first decision being reached within a latency period, the media content clip is provided in accordance with the first decision. In accordance with the latency period being lapsed without the first decision being reached, the media content clip is provided in accordance with the default decision.

Methods, systems and computer program products for automating the association of messages. Data points associated with at least one client device associated with an identifier are logged into an activity database. Labels corresponding to message records are retrieved. Message-signal values representing behavior associated with at least a subset of the message records are also retrieved. The labels are merged with the message-signal values to generate a signal-label collection. A signal-label model is trained based on the signal-label collection, thereby generating a trained signal-label model. A mapping of the one or more activity data points and the plurality of labels are then generated. The embedding that is generated can then be used to find custom audiences.

Ad preference embedding model and lookalike generation engine

Growing community of inventors

Brooklyn, NY, United States of America

David Saverio Susi