Systems and methods for providing content

1. A computer-implemented method comprising:

determining, by a computing system, a plurality of scan versions of a first content item, wherein the plurality of scan versions include at least (i) a first scan version associated with a first number of progressive scans of the first content item and (ii) a second scan version associated with a second number of progressive scans of the first content item that build upon the first number of progressive scans associated with the first scan version;

training, by the computing system, a machine learning model to calculate render scores for different scan versions of content items based on training data, wherein the training data comprises a first set of instances including a content item labeled as a successful render, wherein a successful render is based on a number of scans of the content item transmitted to a device before the content item moved out of view on a display of the device satisfying a threshold value;

calculating, by the computing system, render scores for the plurality of scan versions of the first content item based on the machine learning model, wherein a render score associated with a scan version represents a likelihood that the scan version will render successfully on a first client computing device;

selecting, by the computing system, the first scan version of the plurality of scan versions based on the render scores; and

providing, by the computing system, the first scan version of the first content item to the first client computing device.

2. The computer-implemented method of claim 1 , wherein

the training data further comprises a second set of instances labeled as unsuccessful renders.

3. The computer-implemented method of claim 1 , wherein the machine learning model is configured to calculate a render score for a scan version of a content item based on a file size for the scan version of the content item.

4. The computer-implemented method of claim 1 , wherein the first scan version is selected based on a determination that the first scan version is a scan version of a highest level of quality that also satisfies a render score threshold.

5. The computer-implemented method of claim 1 , further comprising: transmitting, by the computing system, content information to the first client computing device, the content information identifying the first content item and the first scan version of the first content item.

6. The computer-implemented method of claim 5 , wherein the content information identifies a plurality of content items, and scan versions for each content item of the plurality of content items.

7. The computer-implemented method of claim 6 , wherein the content information is transmitted in a JSON file format.

8. The computer-implemented method of claim 5 , further comprising: receiving, by the computing system, from the client computing device a request for the first scan version of the first content item.

9. The computer-implemented method of claim 1 , wherein the first content item is an image encoded in a progressive JPEG format.

10. A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform a method comprising:

determining a plurality of scan versions of a first content item, wherein the plurality of scan versions include at least (i) a first scan version associated with a first number of progressive scans of the first content item and (ii) a second scan version associated with a second number of progressive scans of the first content item that build upon the first number of progressive scans associated with the first scan version;

training a machine learning model to calculate render scores for different scan versions of content items based on training data, wherein the training data comprises a first set of instances including a content item labeled as a successful render, wherein a successful render is based on a number of scans of the content item transmitted to a device before the content item moved out of view on a display of the device satisfying a threshold value;

calculating render scores for the plurality of scan versions of the first content item based on the machine learning model, wherein a render score associated with a scan version represents a likelihood that the scan version will render successfully on a first client computing device;

selecting the first scan version of the plurality of scan versions based on the render scores; and

providing the first scan version of the first content item to the first client computing device.

11. The system of claim 10 , wherein

the training data further comprises a second set of instances labeled as unsuccessful renders.

12. The system of claim 11 , wherein the first scan version is selected based on a determination that the first scan version is a scan version of a highest level of quality that also satisfies a render score threshold.

13. The system of claim 10 , wherein the first content item is an image encoded in a progressive JPEG format.

14. The system of claim 10 , wherein the machine learning model is configured to calculate a render score for a scan version of a content item based on a file size for the scan version of the content item.

15. The system of claim 10 , further comprising: transmitting content information to the first client computing device, the content information identifying the first content item and the first scan version of the first content item.

16. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

determining a plurality of scan versions of a first content item, wherein the plurality of scan versions include at least (i) a first scan version associated with a first number of progressive scans of the first content item and (ii) a second scan version associated with a second number of progressive scans of the first content item that build upon the first number of progressive scans associated with the first scan version;

training a machine learning model to calculate render scores for different scan versions of content items based on training data, wherein the training data comprises a first set of instances including a content item labeled as a successful render, wherein a successful render is based on a number of scans of the content item transmitted to a device before the content item moved out of view on a display of the device satisfying a threshold value;

calculating render scores for the plurality of scan versions of the first content item based on the machine learning model, wherein a render score associated with a scan version represents a likelihood that the scan version will render successfully on a first client computing device;

selecting the first scan version of the plurality of scan versions based on the render scores; and

providing the first scan version of the first content item to the first client computing device.

17. The non-transitory computer-readable storage medium of claim 16 , wherein

the training data further comprises a second set of instances labeled as unsuccessful renders.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the first scan version is selected based on a determination that the first scan version is a scan version of a highest level of quality that also satisfies a render score threshold.

19. The non-transitory computer-readable storage medium of claim 16 , wherein the first content item is an image encoded in a progressive JPEG format.

20. The non-transitory computer-readable storage medium of claim 16 , wherein the machine learning model is configured to calculate a render score for a scan version of a content item based on a file size for the scan version of the content item.