Systems and methods for dynamically identifying illegitimate accounts based on rules

1. A computer-implemented method comprising:

determining, by a computing system, for a set of accounts, one or more feature combinations associated with one or more features relating to the set of accounts;

generating, by the computing system, feature metrics for the one or more feature combinations, the feature metrics based at least in part on a number of disabled accounts in the set of accounts;

determining, by the computing system, threshold values based at least in part on the feature metrics; and

applying, by the computing system, at least one rule for dynamically identifying accounts as being illegitimate, the at least one rule based at least in part on the threshold values.

2. The computer-implemented method of claim 1 , wherein the number of disabled accounts in the set of accounts includes at least one of a manually disabled account or a disabled new account.

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

identifying a particular account not included in the set of accounts;

determining that the particular account is associated with the one or more feature combinations;

determining one or more assessment metrics based at least in part on the feature metrics; and

determining the particular account is illegitimate based on the at least one rule when the one or more assessment metrics satisfy at least one of the threshold values.

4. The computer-implemented method of claim 3 , wherein the one or more assessment metrics are associated with at least one of a ratio of a number of manually disabled new accounts relative to a number of disabled new accounts, a number of new accounts, or a ratio of the number of disabled new accounts relative to the number of new accounts.

5. The computer-implemented method of claim 1 , wherein the threshold values include a first threshold value associated with a ratio of a number of manually disabled new accounts relative to a number of disabled new accounts, a second threshold value associated with a number of new accounts, and a third threshold value associated with a ratio of a number of disabled new accounts relative to a number of new accounts.

6. The computer-implemented method of claim 1 , wherein the set of accounts corresponds to a set of advertiser accounts.

7. The computer-implemented method of claim 1 , wherein the one or more features include at least one of an advertisement title, an advertisement image, an advertisement landing page identifier, a social networking system identifier for an advertisement landing page component, an advertisement body text portion, an advertisement landing page domain, a source internet protocol (IP), a credit card identification number, a latest administered page name, a campaign name, a user agent, or an advertisement image identifier.

8. The computer-implemented method of claim 1 , wherein at least one of the one or more feature combinations includes a default source country, a campaign currency, and a credit card identification number.

9. The computer-implemented method of claim 1 , wherein the threshold values include a first set of threshold values and a second set of threshold values, wherein threshold values in the first set are higher than threshold values in the second set, and wherein the first set of threshold values is associated with automatic disablement, and the second set of threshold values is associated with manual review.

10. The computer-implemented method of claim 1 , wherein the set of accounts is associated with a specified time period.

11. 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:

determining for a set of accounts, one or more feature combinations associated with one or more features relating to the set of accounts;

generating feature metrics for the one or more feature combinations, the feature metrics based at least in part on a number of disabled accounts in the set of accounts;

determining threshold values based at least in part on the feature metrics; and

applying at least one rule for dynamically identifying accounts as being illegitimate, the at least one rule based at least in part on the threshold values.

12. The system of claim 11 , wherein the number of disabled accounts in the set of accounts includes at least one of a manually disabled account or a disabled new account.

13. The system of claim 11 , further comprising:

identifying a particular account not included in the set of accounts;

determining that the particular account is associated with the one or more feature combinations;

determining one or more assessment metrics based at least in part on the feature metrics; and

determining the particular account is illegitimate based on the at least one rule when the one or more assessment metrics satisfy at least one of the threshold values.

14. The system of claim 13 , wherein the one or more assessment metrics are associated with at least one of a ratio of a number of manually disabled new accounts relative to a number of disabled new accounts, a number of new accounts, or a ratio of the number of disabled new accounts relative to the number of new accounts.

15. The system of claim 11 , wherein the threshold values include a first threshold value associated with a ratio of a number of manually disabled new accounts relative to a number of disabled new accounts, a second threshold value associated with a number of new accounts, and a third threshold value associated with a ratio of a number of disabled new accounts relative to a number of new accounts.

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:

determining for a set of accounts, one or more feature combinations associated with one or more features relating to the set of accounts;

generating feature metrics for the one or more feature combinations, the feature metrics based at least in part on a number of disabled accounts in the set of accounts;

determining threshold values based at least in part on the feature metrics; and

applying at least one rule for dynamically identifying accounts as being illegitimate, the at least one rule based at least in part on the threshold values.

17. The non-transitory computer-readable storage medium of claim 16 , wherein the number of disabled accounts in the set of accounts includes at least one of a manually disabled account or a disabled new account.

18. The non-transitory computer-readable storage medium of claim 16 , further comprising:

identifying a particular account not included in the set of accounts;

determining that the particular account is associated with the one or more feature combinations;

determining one or more assessment metrics based at least in part on the feature metrics; and

determining the particular account is illegitimate based on the at least one rule when the one or more assessment metrics satisfy at least one of the threshold values.

19. The non-transitory computer-readable storage medium of claim 18 , wherein the one or more assessment metrics are associated with at least one of a ratio of a number of manually disabled new accounts relative to a number of disabled new accounts, a number of newaccounts, or a ratio of the number of disabled new accounts relative to the number of new accounts.

20. The non-transitory computer-readable storage medium of claim 16 , wherein the threshold values include a first threshold value associated with a ratio of a number of manually disabled new accounts relative to a number of disabled new accounts, a second threshold value associated with a number of new accounts, and a third threshold value associated with a ratio of a number of disabled new accounts relative to a number of new accounts.