Abstract: Systems, methods, and non-transitory computer-readable media can generate individual feature data for each user of a plurality of users. A first cohort comprising a first plurality of users is generated, wherein the first plurality of users are selected from the plurality of users based on the individual feature data. A first set of cohort feature data associated with the first cohort is generated based on individual feature data for the first plurality of users. The first set of cohort feature data and a first set of cohort membership information are transmitted to a modeler. The first set of cohort membership information identifies each user of the plurality of users.

Abstract: The present disclosure is directed toward systems and methods for optimizing view-through conversion rates. For example, systems and methods described herein train and utilize a machine learning model that predicts whether providing a digital impression to a particular networking system user will result in a conversion. Systems and methods described herein identify view-through conversions by generating a vector associated with the provision of a digital impression to a networking system user and receiving third-party conversion information during an attribution window. The systems and methods described herein then utilize the vector and conversion information to train the machine learning model to predict future conversions.

Abstract: An online system receives a data stream of reported interaction events that resulted in each of a desired interaction with a content item. Each reported interaction event is associated with an attribution value defining a portion of a value of a desired interaction that is attributed to the interaction event. Using the attribution values, an attribution model is trained that determines an expected value of presenting the content item associated with the attribution model. The online system uses attribution models of a plurality of candidate content items to select content items for presentation to users of the online system.