Computer-based systems involving machine learning associated with generation of recommended content and methods of use thereof
Systems and methods associated with providing content personalization are disclosed. In one embodiment, an exemplary method may comprise receiving first data including content preferences associated with an audience, receiving second data including an initial digital message being proposed for transmission to the audience, generating a recommendation data set based at least in part on the first data and the second data, wherein the recommendation data set identifies at least one recommended content type and at least one recommended message type, determining via a natural language generation machine learning model suggested content for the audience, and providing the suggested content for dissemination to the audience.
1 . A computer-implemented method, comprising:
receiving, by at least one processor, at least one first message from a remote computing device over a computer network;
automatically extracting, by the at least one processor, a first property by analyzing the at least one first message;
automatically mapping, by the at least one processor via an application programming interface (API), the first property to a content repository stored in a remote content engine to generate a suggested content;
automatically inputting, by the at least one processor, the at least one first message and the suggested content to a machine learning model to generate at least one first image;
wherein the machine learning model is configured to utilize encoded historical images to generate the at least one first image;
automatically modifying, by the at least one processor, at least one user interface to insert the at least one first image into a predetermined banner portion of the at least one user interface, wherein the at least one user interface with the at least one first image is configured to be displayed at the remote computing device;
automatically causing, by the at least one processor, the remote computing device to track at least one action performed to the at least one first image to generate tracking data;
receiving, by the at least one processor, the tracking data from the remote computing device;
updating, by the at least one processor, a dataset with the tracking data; and
providing, by the at least one processor, the updated dataset to re-train the machine learning model.
2 . The method of claim 1 , further comprising inserting the at least one first message along with the at least one first image in the at least one user interface.
3 . The method of claim 1 , wherein the at least one action comprises a tap or click by the at least one user.
4 . The method of claim 1 , further comprising
extracting message type information from the at least one first message; and
providing the message type information to the machine learning model for generating the at least one first image.
5 . The method of claim 1 , wherein the machine learning model is trained with a plurality of banners each associated with a conversion rate.
6 . The method of claim 5 , wherein the machine learning model comprises a convolutional neural network (CNN) for encoding the plurality of banners.
7 . The method of claim 5 , wherein each of the plurality of banners is associated with a message for training the machine learning model.
8 . The method of claim 7 , wherein training the machine learning model comprises extracting message type information from the messages associated with the plurality of banners.
9 . The method of claim 5 , wherein each of the plurality of banners is associated with at least one feature of audiences of the banner for training the machine learning model.
10 . The method of claim 1 , further comprising:
receiving, by the at least one processor, at least one first feature of audiences the at least one first message is aimed at; and
inputting, by the at least one processor, the at least one first feature to the machine learning model for generating the at least one first image.
11 . A system, comprising:
one or more processors; and
a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to:
receive at least one first message from a remote computing device over at least one computer network;
automatically extract a first property by analyzing the at least one first message;
automatically map, via an application programming interface (API), the first property to a content repository stored in a remote content engine to generate a suggested content;
automatically input the at least one first message and the suggested content to a machine learning model to generate at least one first image;
wherein the machine learning model is configured to utilize encoded historical images to generate the at least one first image;
automatically modify at least one user interface to insert the at least one first image into a predetermined banner portion of the at least one user interface, wherein the at least one user interface with the at least one first image is configured to be displayed at the remote computing device;
automatically cause the remote computing device to track at least one action performed to the at least one first image to generate tracking data;
receive the tracking data from the remote computing device;
update a dataset with the tracking data; and
provide the updated dataset to re-train the machine learning model.
12 . The system of claim 11 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to insert the at least one first message along with the at least one first image in the at least one user interface.
13 . The system of claim 1 , wherein the at least one action comprises a tap or click by the at least one user.
14 . The system of claim 11 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
extract a message type information from the at least one first message; and
provide the message type information to the machine learning model for generating the at least one first image.
15 . The system of claim 11 , wherein the machine learning model is trained with a plurality of banners each associated with a conversion rate.
16 . The system of claim 15 , wherein the machine learning model comprises a convolutional neural network (CNN) for encoding the plurality of banners.
17 . The system of claim 15 , wherein each of the plurality of banners is associated with a message for training the machine learning model.
18 . The system of claim 17 , wherein training the machine learning model comprises extracting message type information from the messages associated with the plurality of banners.
19 . The system of claim 15 , wherein each of the plurality of banners is associated with at least one feature of audiences of the banner for training the machine learning model.
20 . The system of claim 11 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
receive at least one first feature of audiences the at least one first message is aimed at; and
input the at least one first feature to the machine learning model for generating the at least one first image.