Abstract: An omni-channel communication request to send communication content to a recipient is received via an application programming interface (API) call. A recipient profile including communication endpoint identifiers associated with the recipient is identified. Each communication endpoint identifier is associated with a respective communication channel. Based on historical user engagement data, a communication channel that is predicted to yield an optimal value of a chosen user engagement metric is selected from among the communication channels. A communication endpoint identifier associated with the communication channel is selected from among the communication endpoint identifiers associated with the recipient. A message including the communication content is then transmitted to the communication endpoint identifier. A set of channel selection rules may be used to select the communication channel in addition to, or instead of, the historical user engagement data.

Abstract: A method for dynamic audience management for omni-channel communications includes receiving an API request to create a messaging audience. The API request specifies values of parameters of the messaging audience. Based on the specified parameter values, a filter definition including criteria for selecting members of the audience from a database is generated. A second API request to transmit a communication to the messaging audience is received. The request specifies a messaging audience generation mode represented by either an ad-hoc audience generation mode or a snapshot audience generation mode. Responsive to determining the mode is the ad-hoc audience generation mode, an audience is generated by applying the filter definition to identify recipients satisfying the criteria. A message including the communication is then transmitted to communication channels corresponding to the identified recipients.

Abstract: Systems and methods for channel selection and personalization based on machine learning models are described herein. The system receives a request to transmit a message to a recipient and identifies destination endpoint identifiers associated with the recipient. The system retrieves historical messaging data from a data store and extracts features comprising message volume metrics and channel-specific delivery metrics. The system associates the recipient with a cluster of recipients based on the extracted features and retrieves channel preference rankings for the cluster. The system selects a communication channel and destination endpoint identifier based on the channel preference rankings, then transmits the message via the selected channel. The system groups recipients based on messaging behavior similarities and derives channel preference rankings from historical delivery success rates and recipient engagement rates within each cluster.