Message-transmittal strategy optimization

Abstract

Methods, systems, and computer programs are presented for the determination of optimal communication scheduling. One method includes an operation for training a machine-learning program to generate a frequency model that determines a frequency for sending communications to users. The training utilizes training data defined by features related to user information and responses of users to previous communications to the users. The method further includes determining, by the frequency model and based on information about a first user, a first frequency for the first user. The first frequency identifies the number of communications to transmit to the first user per period of time. Further, the method includes operations for receiving a communication request to send one or more communications to the first user and determining send times for the one or more communications to the first user based on the first frequency. The communications are sent at the determined send times.

What is claimed is: 
     
         1 . A method comprising:
 training, by one or more processors, a machine-learning program to generate a channel model, the training being based on channels used to send previous communications to users, the generated channel model being configured to determine a preferred channel for sending a communication to a user;   determining, based on the channel model, a first preferred channel for sending a first communication to a first user, the first preferred channel having a score provided by the channel model and indicative of a probability that the first user will engage communications through the first preferred channel; and   causing, by the one or more processors, the first communication to be sent to the first user through the determined first preferred channel.   
     
     
         2 . The method of  claim 1 , further comprising:
 receiving a request to send the first communication to the first user; and wherein:   the determining of the first preferred channel for sending the first communication to the first user is responsive to the received request to send the first communication to the first user.   
     
     
         3 . The method of  claim 1 , wherein:
 the training of the machine-learning program is based on at least one of email data, recipient Internet Protocol (IP) addresses, flags indicating whether the previous communications were read, flags indicating whether links in the previous communications were selected, flags indicating whether recipients unsubscribed from the previous communications, or times when recipients engaged with the previous communications.   
     
     
         4 . The method of  claim 1 , further comprising:
 collecting information about the users and the responses of the users to the previous communications; and   generating training data for the machine-learning program based on the collected information about the users and the responses of the users to the previous communications; and wherein:   the training of the machine-learning program is based on the generated training data.   
     
     
         5 . The method of  claim 1 , wherein:
 the responses of the users to the previous communications include at least one of flags indicating whether the previous communications were read, flags indicating whether links in the previous communications were selected, or flags indicating whether recipients unsubscribed from the previous communications.   
     
     
         6 . The method of  claim 1 , wherein:
 the determining of the first preferred channel for sending the first communication to the first user is based on at least one of a first user profile of the first user or first responses of the first user to previous communications sent to the first user.   
     
     
         7 . The method of  claim 1 , wherein:
 the first communication includes at least one of an email message or a Short Message Service (SMS) message.   
     
     
         8 . A system comprising:
 one or more processors; and   memory storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:   training a machine-learning program to generate a channel model, the training being based on channels used to send previous communications to users, the generated channel model being configured to determine a preferred channel for sending a communication to a user;   determining, based on the channel model, a first preferred channel for sending a first communication to a first user, the first preferred channel having a score provided by the channel model and indicative of a probability that the first user will engage communications through the first preferred channel; and   causing the first communication to be sent to the first user through the determined first preferred channel.   
     
     
         9 . The system of  claim 8 , wherein the operations further comprise:
 receiving a request to send the first communication to the first user; and wherein:   the determining of the first preferred channel for sending the first communication to the first user is responsive to the received request to send the first communication to the first user.   
     
     
         10 . The system of  claim 8 , wherein:
 the training of the machine-learning program is based on at least one of email data, recipient Internet Protocol (IP) addresses, flags indicating whether the previous communications were read, flags indicating whether links in the previous communications were selected, flags indicating whether recipients unsubscribed from the previous communications, or times when recipients engaged with the previous communications.   
     
     
         11 . The system of  claim 8 , wherein the operations further comprise:
 collecting information about the users and the responses of the users to the previous communications; and   generating training data for the machine-learning program based on the collected information about the users and the responses of the users to the previous communications: and wherein:   the training of the machine-learning program is based on the generated training data.   
     
     
         12 . The system of  claim 8 , wherein:
 the responses of the users to the previous communications include at least one of flags indicating whether the previous communications were read, flags indicating whether links in the previous communications were selected, or flags indicating whether recipients unsubscribed from the previous communications.   
     
     
         13 . The system of  claim 8 , wherein:
 the determining of the first preferred channel for sending the first communication to the first user is based on at least one of a first user profile of the first user or first responses of the first user to previous communications sent to the first user.   
     
     
         14 . The system of  claim 8 , wherein:
 the first communication includes at least one of an email message or a Short Message Service (SMS) message.   
     
     
         15 . A non-transitory machine-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
 training a machine-learning program to generate a channel model, the training being based on channels used to send previous communications to users, the generated channel model being configured to determine a preferred. channel for sending a communication to a user;   determining, based on the channel model, a first preferred channel for sending a first communication to a first user, the first preferred channel having a score provided by the channel model and indicative of a probability that the first user will engage communications through the first preferred channel; and   causing the first communication to be sent to the first user through the determined first preferred channel.   
     
     
         16 . The non-transitory machine-readable medium of  claim 15 , wherein the operations further comprise:
 receiving a request to send the first communication to the first user; and wherein:   the determining of the first preferred channel for sending the first communication to the first user is responsive to the received request to send the first communication to the first user.   
     
     
         17 . The non-transitory machine-readable medium of  claim 15 , wherein:
 the training of the machine-learning program is based on at least one of email data, recipient Internet Protocol (IP) addresses, flags indicating whether the previous communications were read, flags indicating whether links in the previous communications were selected, flags indicating whether recipients unsubscribed from the previous communications, or times when recipients engaged with the previous communications.   
     
     
         18 . The non-transitory machine-readable medium of  claim 15 , wherein the operations further comprise:
 collecting information about the users and the responses of the users to the previous communications; and   generating training data for the machine-learning program based on the collected information about the users and the responses of the users to the previous communications; and wherein:   the training of the machine-learning program is based on the generated training data.   
     
     
         19 . The non-transitory machine-readable medium of  claim 15 , wherein:
 the responses of the users to the previous communications include at least one of flags indicating whether the previous communications were read, flags indicating whether links in the previous communications were selected, or flags indicating whether recipients unsubscribed from the previous communications.   
     
     
         20 . The non-transitory machine-readable medium of  claim 15 , wherein:
 the determining of the first preferred channel for sending the first communication to the first user is based on at least one of a first user profile of the first user or first responses of the first user to previous communications sent to the first user.