Systems and methods for tailoring marketing

1. A computer-implemented method comprising:

receiving, by a computing device, a first set of data from a first source and a second set of data from a second source, the first set of data comprising a plurality of items available from the first source for a first set of users and the second set of data comprising transaction purchase data for a second set of users that have reward accounts;

utilizing, by the computing device, a predictive data model that determines a propensity score for a user from only behavior data that is not attributed to the user, the behavior data comprising the second set of data, wherein the user is absent from the second set of users and the propensity score represents a likelihood that the user will act on a recommendation or an offer for one or more of the plurality of items from the first source;

receiving, by the computing device, a third set of data from a third source, the third set of data comprising social media channel data for a third set of users, wherein the third set of users are absent from the second set of users;

updating, by the computing device, the predictive data model to determine the propensity score for the user based at least in part on the third set of data;

generating, with the predictive data model by the computing device, the propensity score for the recommendation or the offer for the user; and

providing, over a computing network, a graphical user interface to the user having the recommendation or the offer in response to the propensity score meeting or exceeding a predefined threshold, wherein a positioning of the recommendation or the offer in the graphical user interface with respect to another recommendation or another offer in the graphical user interface is determined based on social media channel data of the user.

2. The computer-implemented method of claim 1 , wherein generating the propensity score for the recommendation for the user further comprises:

identifying, by the computing device, a plurality of users in the second set of data, individual ones of the plurality of users having a first behavior similar to a second behavior of the user; and

wherein the propensity score is generated based at least in part on a degree of similarity between the first behavior and the second behavior.

3. The computer-implemented method of claim 1 , wherein generating the propensity score for the recommendation for the user further comprises:

identifying, with the predictive data model by the computing device, a predefined dependent variable based at least in part on an analysis of the first set of data or the second set of data; and

wherein the propensity score is generated based at least in part on the predefined dependent variable.

4. The computer-implemented method of claim 1 , wherein generating the propensity score for the recommendation for the user further comprises:

identifying, with the predictive data model by the computing device, a predicted dependent variable based at least in part on an analysis of the first set of data or the second set of data; and

wherein the propensity score is generated based at least in part on the predicted dependent variable.

5. The computer-implemented method of claim 1 , wherein the behavior data for the second set of users represents whether individual ones of the second set of users has one or more purchase transactions involving one or more of the plurality of items available from the first source.

6. The computer-implemented method of claim 1 , further comprising capturing, by an application programming interface (API) that interfaces a social media website or application, the social media channel data of the user.

7. The computer-implemented method of claim 6 , wherein the social media channel data of the user comprises broadcast posts by the user.

8. A system comprising:

a computing device comprising a processor and a memory; and

machine-readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:

receive a first set of data from a first source and a second set of data from a second source, the first set of data comprising a plurality of items available from the first source for a first set of users and the second set of data comprising transaction purchase data for a second set of users that have reward accounts;

utilize a predictive data model that determines a propensity score for a user from only behavior data that is not attributed to the user, the behavior data comprising the second set of data, wherein the user is absent from the second set of users and the propensity score represents a likelihood that the user will act on a recommendation or an offer for one or more of the plurality of items from the first source;

receive a third set of data from a third source, the third set of data comprising social media channel data for a third set of users, wherein the third set of users are absent from the second set of users;

update the predictive data model to determine the propensity score for the user based at least in part on the third set of data;

generate, with the predictive data model, the propensity score for the recommendation or the offer for the user; and

provide, over a computing network, a graphical user interface to the user having the recommendation or the offer in response to the propensity score meeting or exceeding a predefined threshold, wherein a positioning of the recommendation or the offer in the graphical user interface with respect to another recommendation or another offer in the graphical user interface is determined based on social media channel data of the user.

9. The system of claim 8 , wherein the machine-readable instructions that cause the computing device to generate, with the predictive data model, the propensity score for the recommendation for the user further cause the computing device to at least:

identify a plurality of users in the second set of data, individual ones of the plurality of users having a first behavior similar to a second behavior of the user; and

wherein the propensity score is generated based at least in part on a degree of similarity between the first behavior and the second behavior.

10. The system of claim 8 , wherein the machine-readable instructions that cause the computing device to generate, with the predictive data model, the propensity score for the recommendation for the user further cause the computing device to at least:

identify, with the predictive data model, a predefined dependent variable based at least in part on an analysis of the first set of data or the second set of data; and

wherein the propensity score is generated based at least in part on the predefined dependent variable.

11. The system of claim 8 , wherein the machine-readable instructions that cause the computing device to generate, with the predictive data model, the propensity score for the recommendation for the user further cause the computing device to at least:

identify, with the predictive data model, a predicted dependent variable based at least in part on an analysis of the first set of data or the second set of data; and

wherein the propensity score is generated based at least in part on the predicted dependent variable.

12. The system of claim 8 , wherein the behavior data for the second set of users represents whether individual ones of the second set of users has one or more purchase transactions involving one or more of the plurality of items available from the first source.

13. The system of claim 8 , wherein the machine-readable instructions further cause the computing device to capture, using an application programming interface (API) that interfaces a social media website or application, the social media channel data of the user.

14. The system of claim 13 , wherein the social media channel data of the user comprises broadcast posts by the user.

15. A non-transitory, computer-readable medium comprising machine-readable instructions that, when executed by a processor, cause a computing device to at least:

receive a first set of data from a first source and a second set of data from a second source, the first set of data comprising a plurality of items available from the first source for a first set of users and the second set of data comprising transaction purchase data for a second set of users that have reward accounts;

utilize a predictive data model that determines a propensity score for a user from only behavior data that is not attributed to the user, the behavior data comprising the second set of data, wherein the user is absent from the second set of users and the propensity score represents a likelihood that the user will act on a recommendation or an offer for one or more of the plurality of items from the first source;

receive a third set of data from a third source, the third set of data comprising social media channel data for a third set of users, wherein the third set of users are absent from the second set of users;

update the predictive data model to determine the propensity score for the user based at least in part on the third set of data;

generate, with the predictive data model, the propensity score for the recommendation or the offer for the user; and

provide, over a computing network, a graphical user interface to the user having the recommendation or the offer in response to the propensity score meeting or exceeding a predefined threshold, wherein a positioning of the recommendation or the offer in the graphical user interface with respect to another recommendation or another offer in the graphical user interface is determined based on social media channel data of the user.

16. The non-transitory, computer-readable medium of claim 15 , wherein the machine-readable instructions that cause the computing device to generate, with the predictive data model, the propensity score for the recommendation for the user further cause the computing device to at least:

identify a plurality of users in the second set of data, individual ones of the plurality of users having a first behavior similar to a second behavior of the user; and

wherein the propensity score is generated based at least in part on a degree of similarity between the first behavior and the second behavior.

17. The non-transitory, computer-readable medium of claim 15 , wherein the machine-readable instructions that cause the computing device to generate, with the predictive data model, the propensity score for the recommendation for the user further cause the computing device to at least:

identify, with the predictive data model, a predefined dependent variable based at least in part on an analysis of the first set of data or the second set of data; and

wherein the propensity score is generated based at least in part on the predefined dependent variable.

18. The non-transitory, computer-readable medium of claim 15 , wherein the machine-readable instructions that cause the computing device to generate, with the predictive data model, the propensity score for the recommendation for the user further cause the computing device to at least:

identify, with the predictive data model, a predicted dependent variable based at least in part on an analysis of the first set of data or the second set of data; and

wherein the propensity score is generated based at least in part on the predicted dependent variable.

19. The non-transitory, computer-readable medium of claim 15 , wherein the behavior data for the second set of users represents whether individual ones of the second set of users has one or more purchase transactions involving one or more of the plurality of items available from the first source.

20. The non-transitory, computer-readable medium of claim 15 , wherein the machine-readable instructions further cause the computing device to capture, using an application programming interface (API) that interfaces a social media website or application, the social media channel data of the user.