Systems and methods for utilizing unused network capacity for prefetch requests

1. A computer-implemented method for utilizing unused network capacity for prefetch requests, the method comprising:

receiving, over a network at one or more servers, unused network capacity information from a network provider of the network;

determining, by the one or more servers, a threshold value for approving a candidate prefetch request based on the received unused network capacity information;

receiving, over the network at the one or more servers, a plurality of candidate prefetch requests from an application running on a device connected to the network of the network provider;

determining, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, a likelihood-of-use score for the candidate prefetch request, the likelihood-of-use score for the candidate prefetch request being based on a likelihood that a user of a device will request data associated with the candidate prefetch request; and

approving or not approving, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, the candidate prefetch request being based on the determined threshold value and the determined likelihood-of-use score for the candidate prefetch request.

2. The method of claim 1 , wherein the threshold value is a predetermined percentage of the determined unused network capacity.

3. The method of claim 1 , further comprising:

receiving, over the network by the one or more servers, a plurality of content requests from the user of the application running on the device; and

building, by the one or more servers, a prefetch model for the user of the device based on the received plurality of content requests and the received plurality of candidate prefetch requests.

4. The method of claim 3 , further comprising:

comparing, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, the candidate prefetch request to the prefetch model,

wherein determining the likelihood-of-use score for the candidate prefetch request based on the received plurality of candidate prefetch requests comprises:

determining, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, a likelihood-of-use score for the candidate prefetch request based on the received plurality of candidate prefetch requests and the prefetch model when the candidate prefetch request matches the prefetch model.

5. The method of claim 1 , wherein responding to candidate prefetch request based on the determined threshold value and the determined likelihood-of-use score for the candidate prefetch request includes:

transmitting, over the network by the one or more servers, instructions to a server of the network provider to provide a response to candidate prefetch request based on the determined threshold value and the determined likelihood-of-use score for the candidate prefetch request.

6. A system for utilizing unused network capacity for prefetch requests, the system including:

a data storage device that stores instructions for utilizing unused network capacity for prefetch requests; and

a processor configured to execute the instructions to perform a method including:

receiving, over a network at one or more servers, unused network capacity information from a network provider of the network;

determining, by the one or more servers, a threshold value for approving a candidate prefetch request based on the received unused network capacity information;

receiving, over the network at the one or more servers, a plurality of candidate prefetch requests from an application running on a device connected to the network of the network provider;

determining, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, a likelihood-of-use score for the candidate prefetch request, the likelihood-of-use score for the candidate prefetch request being based on a likelihood that a user of a device will request data associated with the candidate prefetch request; and

approving or not approving, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, the candidate prefetch request being based on the determined threshold value and the determined likelihood-of-use score for the candidate prefetch request.

7. The system of claim 6 , wherein the threshold value is a predetermined percentage of the determined unused network capacity.

8. The system of claim 6 , wherein the processor is further configured to execute the instructions to perform the method including:

receiving, over the network by the one or more servers, a plurality of content requests from the user of the application running on the device; and

building, by the one or more servers, a prefetch model for the user of the device based on the received plurality of content requests and the received plurality of candidate prefetch requests.

9. The system of claim 8 , further comprising:

comparing, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, the candidate prefetch request to the prefetch model,

wherein determining the likelihood-of-use score for the candidate prefetch request based on the received plurality of candidate prefetch requests comprises:

determining, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, a likelihood-of-use score for the candidate prefetch request based on the received plurality of candidate prefetch requests and the prefetch model when the candidate prefetch request matches the prefetch model.

10. The system of claim 6 , wherein responding to candidate prefetch request based on the determined threshold value and the determined likelihood-of-use score for the candidate prefetch request includes:

transmitting, over the network by the one or more servers, instructions to a server of the network provider to provide a response to candidate prefetch request based on the determined threshold value and the determined likelihood-of-use score for the candidate prefetch request.

11. A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause the computer to perform a method for utilizing unused network capacity for prefetch requests, the method including:

receiving, over a network at one or more servers, unused network capacity information from a network provider of the network;

determining, by the one or more servers, a threshold value for approving a candidate prefetch request based on the received unused network capacity information;

receiving, over the network at the one or more servers, a plurality of candidate prefetch requests from an application running on a device connected to the network of the network provider;

determining, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, a likelihood-of-use score for the candidate prefetch request, the likelihood-of-use score for the candidate prefetch request being based on a likelihood that a user of a device will request data associated with the candidate prefetch request; and

approving or not approving, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, the candidate prefetch request being based on the determined threshold value and the determined likelihood-of-use score for the candidate prefetch request.

12. The computer-readable medium of claim 11 , wherein the threshold value is a predetermined percentage of the determined unused network capacity.

13. The computer-readable medium of claim 11 , further comprising:

receiving, over the network by the one or more servers, a plurality of content requests from the user of the application running on the device; and

building, by the one or more servers, a prefetch model for the user of the device based on the received plurality of content requests and the received plurality of candidate prefetch requests.

14. The computer-readable medium of claim 13 , further comprising:

comparing, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, the candidate prefetch request to the prefetch model,

wherein determining the likelihood-of-use score for the candidate prefetch request based on the received plurality of candidate prefetch requests comprises:

determining, for each candidate prefetch request of the plurality of candidate prefetch requests by the one or more servers, a likelihood-of-use score for the candidate prefetch request based on the received plurality of candidate prefetch requests and the prefetch model when the candidate prefetch request matches the prefetch model.