Customized agreement generation

1. A method comprising:

receiving, by one or more processors, a request for a document from a client device of a receiving entity;

applying, by the one or more processors, a machine-learned model to a representation of a feature of a profile characterizing the receiving entity and a target rendering parameter for rendering content of the document;

receiving, by the one or more processors and as an output from the machine-learned model, a likelihood that an interaction with the document rendered for display with the target rendering parameter is performed by the receiving entity causing a completion of the document;

modifying, by the one or more processors and based on the likelihood, the document to render the content for display with the target rendering parameter; and

providing, by the one or more processors, the modified document to the client device.

2. The method of claim 1 , further comprising:

selecting, by the one or more processors and using the machine-learned model, a template of a plurality of templates, the selected template associated with a threshold likelihood for historical receiving entities to complete documents generated from the selected template; and

generating, by the one or more processors, the document using the selected template.

3. The method of claim 1 , further comprising:

creating, by the one or more processors, a plurality of templates using the machine-learned model, each template including a respective plurality of rendering parameters.

4. The method of claim 1 , further comprising:

training, by the one or more processors, the machine-learned model using historical documents and profiles of historical receiving entities to which the historical documents were provided for completion.

5. The method of claim 4 , further comprising generating, by the one or more processors, the profiles of historical receiving entities using tracked user interactions with the historical documents.

6. The method of claim 5 , further comprising:

tracking, by the one or more processors, the user interactions, wherein the user interactions include one or more of a percentage of a historical document accessed by a historical receiving entity using a corresponding client device, a duration of time that the historical document was displayed at the corresponding client device, or a click to complete the historical document.

7. The method of claim 1 ,

wherein the profile includes an accessibility feature indicating a preference for accessing the document to accommodate a physical impairment.

8. The method of claim 1 ,

wherein the profile includes a location feature indicating a geographic area in which the receiving entity resides.

9. The method of claim 1 , further comprising, in response to receiving a notification that the receiving entity has completed the modified document:

storing, by the one or more processors, a mapping of a completion certificate and a plurality of rendering parameters for rendering the content of the document before the modifying and the target rendering parameter.

10. The method of claim 1 , wherein providing the modified document comprises generating, by the one or more processors, an inline frame (iframe) including the modified document.

11. The method of claim 1 , wherein the document is generated in a secured domain characterized by one or more of:

the one or more processors being centralized;

authentication requirements being enforced by the one or more processors;

malware protection for the one or more processors;

encryption of the document; or

secured access to the document.

12. The method of claim 1 , wherein the document is completed in response to the receiving entity providing a user input via the client device indicating an agreement to terms of the document.

13. The method of claim 1 , wherein the representation includes a feature vector comprising a plurality of dimensions, a subset of the plurality of dimensions corresponding to a plurality of rendering parameters for rendering the content of the document before the modifying, and the feature.

14. Non-transitory computer-readable storage media storing executable instructions that, when executed by one or more processors, cause the one or more processors to:

receive a request for a document from a client device of a receiving entity;

apply a machine-learned model to a representation of a feature of a profile characterizing the receiving entity and a target rendering parameter for rendering content of the document;

receive, as an output from the machine-learned model, a likelihood that an interaction with the document rendered for display with the target rendering parameter is performed by the receiving entity causing a completion of the document;

modify, based on the likelihood, the document to render the content for display with the target rendering parameter; and

provide the modified document to the client device.

15. The non-transitory computer-readable storage media of claim 14 , wherein the instructions further cause the one or more processors to:

select, using the machine-learned model, a template of a plurality of templates, the selected template associated with a threshold likelihood for historical receiving entities to complete documents generated from the selected template; and

generate the document using the selected template.

16. The non-transitory computer-readable storage media of claim 14 , wherein the instructions further cause the one or more processors to:

create a plurality of templates using the machine-learned model, each template including a respective plurality of rendering parameters.

17. The non-transitory computer-readable storage media of claim 14 , wherein the instructions further cause the one or more processors to:

train the machine-learned model using historical documents and profiles of historical receiving entities to which the historical documents were provided for completion.

18. The non-transitory computer-readable storage media of claim 17 , wherein the instructions further cause the one or more processors to generate the profiles of historical receiving entities using tracked user interactions with the historical documents.

19. A system comprising one or more processors and non-transitory computer-readable storage media storing instructions that, when executed by the one or more processors, cause the one or more processors to:

receive a request for a document from a client device of a receiving entity;

apply a machine-learned model to a representation of a feature of a profile characterizing the receiving entity and a target rendering parameter for rendering content of the document;

receive, as an output from the machine-learned model, a likelihood that an interaction with the document rendered for display with the target rendering parameter is performed by the receiving entity causing a completion of the document;

modify, based on the likelihood, the document to render the content for display with the target rendering parameter; and

provide the modified document to the client device.

20. The system of claim 19 , wherein the instructions further cause the one or more processors to:

select, using the machine-learned model, a template of a plurality of templates, the selected template associated with a threshold likelihood for historical receiving entities to complete documents generated from the selected template; and

generate the document using the selected template.