Generating Personalized Messages According To Campaign Data
In one embodiment, a method includes receiving a request to initiate a messaging campaign. The request may comprise campaign rules. The method may also include sending, to each of several users, one or more messages associated with the messaging campaign; receiving, from each of the users, a response to each of the messages; updating campaign data associated with the messaging campaign based on the responses from each of the plurality of users; accessing user data associated with a first user of a social-networking system; accessing the updated campaign data of the users; and determining, by a machine-learning model, a message associated with the messaging campaign. The message may be based on the user data of the first user and the updated campaign data, and satisfies the one or more rules for the messaging campaign. Finally, the method may include generating the message for presentation to the first user.
1 . A method comprising:
receiving, from a client device of an entity, a request to initiate a messaging campaign, wherein the request comprises one or more campaign rules for the messaging campaign;
sending, to each of a plurality of users, one or more messages associated with the messaging campaign;
receiving, from each of the plurality of users, a response to each of the one or more messages;
updating campaign data associated with the messaging campaign based on the responses from each of the plurality of users;
accessing user data associated with a first user of a social-networking system;
accessing the updated campaign data of the plurality of users;
determining, by a machine-learning model, a message associated with the messaging campaign, wherein the message:
is based on the user data of the first user and the updated campaign data of the plurality of users; and
satisfies the one or more rules for the messaging campaign; and
generating the message for presentation to the first user.
2 . The method of claim 1 , further comprising sending the message to a client device associated with the first user.
3 . The method of claim 1 , wherein the user data comprises conversion data or social-networking data specific to the first user.
4 . The method of claim 1 , wherein the campaign rules comprise a start date of the campaign and an end date of the campaign.
5 . The method of claim 1 , wherein the machine learning model is trained using data from lookalike users with respect to the first user, wherein:
the lookalike users are selected from a plurality of second users;
wherein the first user corresponds to a first user-vector and the plurality of second users correspond to a plurality of second user-vectors, respectively;
each user-vector is an N-dimensional vector representing the respective user in an N-dimensional vector space, each dimension of the user-vector corresponding to a social-networking trait of the respective user, and
each lookalike user is selected based on a vector similarity between the first user-vector and the second-user vector corresponding to the lookalike user.
6 . The method of claim 1 , wherein the campaign rules comprise a rule to modify the message if the messaging campaign is within a threshold number of days from an end date of the messaging campaign.
7 . The method of claim 1 , wherein the one or more campaign rules comprise a discount range on an offer within the message.
8 . The method of claim 7 , wherein the campaign rules comprise a rule to increase the discount if the messaging campaign is within a threshold number of days from an end date of the messaging campaign.
9 . One or more computer-readable non-transitory storage media comprising software that is operable when executed to:
receive, from a client device of an entity, a request to initiate a messaging campaign, wherein the request comprises one or more campaign rules for the messaging campaign;
send, to each of a plurality of users, one or more messages associated with the messaging campaign;
receive, from each of the plurality of users, a response to each of the one or more messages;
update campaign data associated with the messaging campaign based on the responses from each of the plurality of users;
access user data associated with a first user of a social-networking system;
access the updated campaign data of the plurality of users;
determine, by a machine-learning model, a message associated with the messaging campaign, wherein the message:
is based on the user data of the first user and the updated campaign data of the plurality of users; and
satisfies the one or more rules for the messaging campaign; and
generating the message for presentation to the first user.
10 . The media of claim 9 , wherein the software is further operable when executed to send the message to a client device associated with the first user.
11 . The media of claim 9 , wherein the user data comprises conversion data or social-networking data specific to the first user.
12 . The media of claim 9 , wherein the campaign rules comprise a start date of the campaign and an end date of the campaign.
13 . The media of claim 9 , wherein the machine learning model is trained using data from lookalike users with respect to the first user, wherein:
the lookalike users are selected from a plurality of second users;
wherein the first user corresponds to a first user-vector and the plurality of second users correspond to a plurality of second user-vectors, respectively;
each user-vector is an N-dimensional vector representing the respective user in an N-dimensional vector space, each dimension of the user-vector corresponding to a social-networking trait of the respective user, and
each lookalike user is selected based on a vector similarity between the first user-vector and the second-user vector corresponding to the lookalike user.
14 . The media of claim 9 , wherein the campaign rules comprise a rule to modify the message if the messaging campaign is within a threshold number of days from an end date of the messaging campaign.
15 . The media of claim 9 , wherein the one or more campaign rules comprise a discount range on an offer within the message.
16 . The method of claim 15 , wherein the campaign rules comprise a rule to increase the discount if the messaging campaign is within a threshold number of days from an end date of the messaging campaign.
17 . A system comprising:
one or more processors; and
one or more computer-readable non-transitory storage media coupled to one or more of the processors and comprising instructions operable when executed by one or more of the processors to cause the system to:
receive, from a client device of an entity, a request to initiate a messaging campaign, wherein the request comprises one or more campaign rules for the messaging campaign;
send, to each of a plurality of users, one or more messages associated with the messaging campaign;
receive, from each of the plurality of users, a response to each of the one or more messages;
update campaign data associated with the messaging campaign based on the responses from each of the plurality of users;
access user data associated with a first user of a social-networking system;
access the updated campaign data of the plurality of users;
determine, by a machine-learning model, a message associated with the messaging campaign, wherein the message:
is based on the user data of the first user and the updated campaign data of the plurality of users; and
satisfies the one or more rules for the messaging campaign; and
generating the message for presentation to the first user.
18 . The system of claim 17 , wherein the software is further operable when executed to send the message to a client device associated with the first user.
19 . The system of claim 17 , wherein the user data comprises conversion data or social-networking data specific to the first user.
20 . The system of claim 17 , wherein the campaign rules comprise a start date of the campaign and an end date of the campaign.