Determine a strategic digital content transmission time using recurrent neural networks and a survival analysis

摘要

Disclosed are methods, systems and non-temporary computer readable storage media for determining and applying digital content transfer times using machine learning. In one or more embodiments, the disclosed system trains a recurrent neural network, for example, based on past electronic communications for a user that has been divided into multiple time classes. In addition, in one or more embodiments, the system utilizes the trained recurrent neural network to generate predictions of activity metrics (eg, a survival analysis or an interaction probability metric risk metric) for sending a new electronic message within the plurality of time classes. The system then executes the digital content campaign by selecting a time class based on the predicted activity metrics and then sending the new electronic message at a broadcast time corresponding to the selected time class.