Systems and methods for using machine learning models to organize and select modular components for user interface templates

1. A system for using machine learning models to organize and select modular components for user interface templates, the system comprising:

cloud-based storage circuitry for storing a user profile corresponding to a user account;

cloud-based control circuitry for:

receive a request for a user interface that meets template requirements and comprises a preferred number of user input fields or a preferred number of user interface pages;

determine a plurality of categories of account characteristics required to be populated to meet the template requirements;

in response to receiving the request, retrieve a user profile corresponding to a user account for a user;

filter the plurality of categories based on whether any of the plurality of categories is populated by known account characteristics for user accounts retrieved from user profiles;

determine, using a machine learning model, a first output, wherein the first output indicates the preferred number of user input fields or the preferred number of user interface pages; and

generate for display, on a user device, the user interface comprising the preferred number of user input fields or the preferred number of user interface pages; and

cloud-based control circuitry for generating for display, on a user device, the user interface comprising the preferred number of user input fields and the preferred number of user interface pages, wherein the preferred number of user input fields are arranged as modular components on each page of the preferred number of user interface pages.

2. A method for using machine learning models to organize and select modular components for user interface templates, the method comprising:

receiving a request for a user interface that meets template requirements and comprises a preferred number of user input fields or a preferred number of user interface pages;

determining a plurality of categories of account characteristics required to be populated to meet the template requirements;

in response to receiving the request, retrieving a user profile corresponding to a user account for a user;

filtering the plurality of categories based on whether any of the plurality of categories is populated by known account characteristics for user accounts retrieved from user profiles;

determining, using a machine learning model, a first output, wherein the first output indicates the preferred number of user input fields or the preferred number of user interface pages; and

generating for display, on a user device, the user interface comprising the preferred number of user input fields or the preferred number of user interface pages.

3. The method of claim 2 , wherein the machine learning model is trained to determine a number of user input fields and a number of user interface pages with a predetermined probability of completion by a user corresponding to the user account.

4. The method of claim 3 , wherein determining the number of user input fields and the number of user interface pages with the predetermined probability of completion by the user corresponding to the user account comprises:

determining a first number of user input fields at which the user likely stops completing user interfaces;

determining a first number of user interface pages at which the user likely stops completing user interfaces; and

determining the preferred number of user input fields and the preferred number of user interface pages based on the first number of user input fields and the first number of user interface pages.

5. The method of claim 3 , wherein determining the number of user input fields and the number of user interface pages with the predetermined probability of completion by the user corresponding to the user account comprises:

determining a respective probability corresponding to each number of user input fields at which the user likely stops completing user interfaces;

determining a respective probability corresponding to each number of user interface pages at which the user likely stops completing user interfaces; and

determining the preferred number of user input fields and the preferred number of user interface pages based on the respective probability corresponding to each number of user input fields, and the respective probability corresponding to each number of user interface pages.

6. The method of claim 2 , wherein predetermined probability of completion by the user corresponding to the user account is based on a behavior characteristic of the user retrieved from the user profile.

7. The method of claim 2 , wherein the user profile includes a behavior characteristic and an account characteristic, wherein the behavior characteristic indicates likely user behavior when interacting with user interfaces, and wherein the account characteristic indicates a current status of a category of information of the user account.

8. The method of claim 2 , further comprising:

generating a first feature input based on the user profile and the template requirements;

inputting the first feature input into a machine learning model, wherein the machine learning model is trained to:

determine a plurality of categories of account characteristics required to be populated to meet the template requirements;

filter the plurality of categories based on whether any of the plurality of categories is populated by known account characteristics for user accounts retrieved from user profiles;

determine for the filtered plurality of categories a number of user input fields and a number of user interface pages based on known behavior characteristics for user accounts retrieved from user profiles.

9. The method of claim 2 , wherein the machine learning model is further trained to:

determine a first category of the plurality of categories at which the user likely stops completing user interfaces; and

filter the plurality of categories based on the first category.

10. The method of claim 2 , wherein the machine learning model is further trained to:

determine respective probabilities of various orders of input fields at which the user likely stops completing user interfaces, wherein the first output indicates a preferred order of user input fields, and wherein the user interface comprises the preferred number of user input fields and the preferred number of user interface pages in the preferred order; or

determine respective probabilities of various orders of pages at which the user likely stops completing user interfaces, wherein the first output indicates a preferred order of pages, and wherein the user interface comprises the preferred number of user input fields and the preferred number of user interface pages in the preferred order of pages.

11. The method of claim 2 , further comprising:

retrieving a first additional user profile corresponding to the user account from a third party microservice;

retrieving a second additional user profile corresponding to the user account from a website cookie; and

aggregating information from the user profile, the first additional user profile, and the second additional user profile.

12. A non-transitory, computer readable medium for using machine learning models to organize and select modular components for user interface templates comprising instructions that when executed on one or more processors cause operations comprising:

receiving a request for a user interface that meets template requirements and comprises a preferred number of user input fields or a preferred number of user interface pages;

determining a plurality of categories of account characteristics required to be populated to meet the template requirements;

in response to receiving the request, retrieving a user profile corresponding to a user account for a user;

filtering the plurality of categories based on whether any of the plurality of categories is populated by known account characteristics for user accounts retrieved from user profiles;

determining, using a machine learning model, a first output, wherein the first output indicates the preferred number of user input fields or the preferred number of user interface pages; and

generating for display, on a user device, the user interface comprising the preferred number of user input fields or the preferred number of user interface pages.

13. The non-transitory, computer readable medium of claim 12 , wherein the machine learning model is trained to determine a number of user input fields and a number of user interface pages with a predetermined probability of completion by a user corresponding to the user account.

14. The non-transitory, computer readable medium of claim 13 , wherein determining the number of user input fields and the number of user interface pages with the predetermined probability of completion by the user corresponding to the user account comprises:

determining a first number of user input fields at which the user likely stops completing user interfaces;

determining a first number of user interface pages at which the user likely stops completing user interfaces; and

determining the preferred number of user input fields and the preferred number of user interface pages based on the first number of user input fields and the first number of user interface pages.

15. The non-transitory, computer readable medium of claim 13 , wherein determining the number of user input fields and the number of user interface pages with the predetermined probability of completion by the user corresponding to the user account comprises:

determining a respective probability corresponding to each number of user input fields at which the user likely stops completing user interfaces;

determining a respective probability corresponding to each number of user interface pages at which the user likely stops completing user interfaces; and

determining the preferred number of user input fields and the preferred number of user interface pages based on the respective probability corresponding to each number of user input fields, and the respective probability corresponding to each number of user interface pages.

16. The non-transitory, computer readable medium of claim 13 , wherein predetermined probability of completion by the user corresponding to the user account is based on a behavior characteristic of the user retrieved from the user profile.

17. The non-transitory, computer readable medium of claim 12 , wherein the user profile includes a behavior characteristic and an account characteristic, wherein the behavior characteristic indicates likely user behavior when interacting with user interfaces, and wherein the account characteristic indicates a current status of a category of information of the user account.

18. The non-transitory, computer readable medium of claim 12 , wherein the instructions further cause operation comprising:

generating a first feature input based on the user profile and the template requirements;

inputting the first feature input into a machine learning model, wherein the machine learning model is trained to:

determine a plurality of categories of account characteristics required to be populated to meet the template requirements;

filter the plurality of categories based on whether any of the plurality of categories is populated by known account characteristics for user accounts retrieved from user profiles;

determine for the filtered plurality of categories a number of user input fields and a number of user interface pages based on known behavior characteristics for user accounts retrieved from user profiles.

19. The non-transitory, computer readable medium of claim 12 , wherein the machine learning model is further trained to:

determine a first category of the plurality of categories at which the user likely stops completing user interfaces; and

filter the plurality of categories based on the first category.

20. The non-transitory, computer readable medium of claim 12 , wherein the machine learning model is further trained to:

determine respective probabilities of various orders of input fields at which the user likely stops completing user interfaces, wherein the first output indicates a preferred order of user input fields, and wherein the user interface comprises the preferred number of user input fields and the preferred number of user interface pages in the preferred order; or

determine respective probabilities of various orders of pages at which the user likely stops completing user interfaces, wherein the first output indicates a preferred order of pages, and wherein the user interface comprises the preferred number of user input fields and the preferred number of user interface pages in the preferred order of pages.