Systems and methods for scraping URLs based on viewport views

1. A computer-implemented method comprising:

receiving, by a computing system, a uniform resource locator;

determining, by the computing system, a predicted time of when a cold start state for a first machine learning model will end based on a quantity of training views associated with the uniform resource locator;

providing, by the computing system, to the first machine learning model, a time and one or more features associated with the uniform resource locator based on the predicted time, wherein the one or more features include historical data associated with a domain referenced by the uniform resource locator; and

receiving, by the computing system, from the first machine learning model, a prediction relating to a quantity of views the uniform resource locator achieves by the time.

2. The computer-implemented method of claim 1 , further comprising:

determining, by the computing system, the cold start state to have ended based on the quantity of training views satisfying a threshold quantity of training views.

3. The computer-implemented method of claim 1 , further comprising:

determining, by the computing system, that the prediction relating to a quantity of views satisfies a threshold quantity of views; and

requesting, by the computing system, that the uniform resource locator be scraped.

4. The computer-implemented method of claim 1 , wherein the one or more features comprise at least one of: an identifier or one or more tokens.

5. The computer-implemented method of claim 1 , further comprising:

providing, by the computing system, to the first machine learning model, training data input comprising an elapsed time and one or more features which correspond to the uniform resource locator; and

providing, by the computing system, to the first machine learning model, training data output comprising view count data for the uniform resource locator.

6. The computer-implemented method of claim 1 , wherein the uniform resource locator references at least one of: a page, a profile, a group, or a webpage.

7. The computer-implemented method of claim 1 , wherein the first machine learning model applies Poisson regression.

8. The computer-implemented method of claim 1 , further comprising:

providing, by the computing system, to a second machine learning model, one or more features associated with the uniform resource locator; and

receiving, by the computing system, from the second machine learning model, a second prediction, wherein the second prediction relates to a quantity of views the uniform resource locator achieves before the cold start state ends.

9. The computer-implemented method of claim 1 , wherein the cold start state is associated with the first machine learning model having not yet been trained with a threshold quantity of training views and the predicted time is associated with when the first machine learning model will be trained with the threshold quantity of training views.

10. The computer-implemented method of claim 8 , further comprising:

determining, by the computing system, that the second prediction satisfies a second threshold quantity of views; and

requesting, by the computing system, that the uniform resource locator be scraped.

11. A computer-implemented 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:

receiving a uniform resource locator;

determining a predicted time of when a cold start state for a first machine learning model will end based on a quantity of training views associated with the uniform resource locator;

providing, to the first machine learning model, a time and one or more features associated with the uniform resource locator based on the predicted time, wherein the one or more features include historical data associated with a domain referenced by the uniform resource locator; and

receiving, from the first machine learning model, a prediction relating to a quantity of views the uniform resource locator achieves by the time.

12. The system of claim 11 , wherein the instructions, when executed by the at least one processor, further cause the system to perform:

determining that the prediction relating to a quantity of views satisfies a threshold quantity of views; and

requesting that the uniform resource locator be scraped.

13. The system of claim 11 , wherein the instructions, when executed by the at least one processor, further cause the system to perform:

providing, to a second machine learning model, one or more features associated with the uniform resource locator; and

receiving, from the second machine learning model, a second prediction, wherein the second prediction relates to a quantity of views the uniform resource locator achieves before the cold start state ends.

14. The system of claim 11 , wherein the cold start state is associated with the first machine learning model having not yet been trained with a threshold quantity of training views and the predicted time is associated with when the first machine learning model will be trained with the threshold quantity of training views.

15. The system of claim 13 , wherein the instructions, when executed by the at least one processor, further cause the system to perform:

determining that the second prediction satisfies a second threshold quantity of views; and

requesting that the uniform resource locator be scraped.

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:

receiving a uniform resource locator;

determining a predicted time of when a cold start state for a first machine learning model will end based on a quantity of training views associated with the uniform resource locator;

providing, to the first machine learning model, a time and one or more features associated with the uniform resource locator based on the predicted time, wherein the one or more features include historical data associated with a domain referenced by the uniform resource locator; and

receiving, from the first machine learning model, a prediction relating to a quantity of views the uniform resource locator achieves by the time.

17. The non-transitory computer-readable storage medium of claim 16 , wherein the instructions, when executed by the at least one processor of the computing system, further cause the computing system to perform:

determining that the prediction relating to a quantity of views satisfies a threshold quantity of views; and

requesting that the uniform resource locator be scraped.

18. The non-transitory computer-readable storage medium of claim 16 , wherein the instructions, when executed by the at least one processor of the computing system, further cause the computing system to perform:

providing, to a second machine learning model, one or more features associated with the uniform resource locator; and

receiving, from the second machine learning model, a second prediction, wherein the second prediction relates to a quantity of views the uniform resource locator achieves before the cold start state ends.

19. The non-transitory computer-readable storage medium of claim 18 , wherein the cold start state is associated with the first machine learning model having not yet been trained with a threshold quantity of training views and the predicted time is associated with when the first machine learning model will be trained with the threshold quantity of training views.

20. The non-transitory computer-readable storage medium of claim 18 , wherein the instructions, when executed by the at least one processor of the computing system, further cause the computing system to perform:

determining that the second prediction satisfies a second threshold quantity of views; and

requesting that the uniform resource locator be scraped.