System and method for identifying abusive account registration
Disclosed is a system and method for processing account registration by identifying account candidates attempting to open an account as abusive. That is, the present disclosure discusses identifying, and challenging and marking abusive account registration. The present disclosure takes into account users' behaviors on a network and the impact to the cost and/or revenue of the network. The present disclosure is proactive as it allows for actions to be taken at the earliest possible time in the registration process before an account is created. This prevents abusive activity from taking place within the network and effecting services and privileges available to legitimate users. Additionally, the effects of the disclosed systems and methods minimize the negative impacts of abusive activity on normal user accounts.
1. A method comprising:
receiving, at a computing device, a new account registration request from a user, said registration request comprising user provided registration information associated with the user;
extracting, via the computing device, features of the user provided registration information; and
examining, via the computing device, said features to determine whether said request is for a legitimate or abusive purpose, said examination comprising comparing said features against labeled information associated with an existing account, said labeled information corresponding to a multi-dimensional feature vector associated with raw data collected from the existing account,
when said features are determined to correspond to an abusive purpose, deny said account registration request, and
when said features are determined to correspond to a legitimate purpose, grant said account registration request.
2. The method of claim 1 , wherein said raw data comprises user activity data associated with said existing account, said user activity data being extracted from said existing account.
3. The method of claim 2 , wherein said multi-dimensional feature vector is based on an identified pattern of activity derived from said user activity data, said pattern providing an indication as to whether said existing account is legitimate or abusive, said labeled information comprising said indication.
4. The method of claim 1 , further comprising analyzing said new account registration request based on said examination, said analysis comprises training a classifier with said determination of the purpose of the request.
5. The method of claim 4 , further comprising updating the multi-dimensional feature vector based on said analysis of said new account registration, wherein said updating occurs continuously upon determinations of new account requests.
6. The method of claim 4 , further comprising applying said updated multi-dimensional feature vector via the classifier to a subsequent account registration request.
7. The method of claim 6 , wherein the classifier implements machine learning techniques in accordance with the multi-dimensional feature vector.
8. The method of claim 1 , further comprising:
labelling said new account registration request based on said examination; and
updating an account database based on said labelling, said account database comprising user account information for user accounts on the network.
9. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions, that when executed by a computer, perform a method comprising:
receiving a new account registration request from a user, said registration request comprising user provided registration information associated with the user;
extracting features of the user provided registration information; and
examining said features to determine whether said request is for a legitimate or abusive purpose, said examination comprises comparing said features against labeled information associated with an existing account, said labeled information corresponding to a multi-dimensional feature vector associated with raw data collected from the existing account,
when said features are determined to correspond to an abusive purpose, deny said account registration request, and
when said features are determined to correspond to a legitimate purpose, grant said account registration request.
10. The non-transitory computer-readable storage medium of claim 9 , wherein said raw data comprises user activity data associated with said existing account, said user activity data being extracted from said existing account.
11. The non-transitory computer-readable storage medium of claim 10 , wherein said multi-dimensional feature vector is based on an identified pattern of activity derived from said user activity data, said pattern providing an indication as to whether said existing account is legitimate or abusive, said labeled information comprising said indication.
12. The non-transitory computer-readable storage medium of claim 9 , further comprising analyzing said new account registration request based on said examination, said analysis comprises training a classifier with said determination of the purpose of the request.
13. The non-transitory computer-readable storage medium of claim 12 , further comprising:
updating the multi-dimensional feature vector based on said analysis of said new account registration, wherein said updating occurs continuously upon determinations of new account requests; and
applying said updated multi-dimensional feature vector via the classifier to a subsequent account registration request.
14. The non-transitory computer-readable storage medium of claim 13 , wherein the classifier implements machine learning techniques in accordance with the multi-dimensional feature vector.
15. The non-transitory computer-readable storage medium of claim 9 , further comprising:
labelling said new account registration request based on said examination; and
updating an account database based on said labelling, said account database comprising user account information for user accounts on the network.
16. A system comprising:
at least one computing device comprising:
memory storing computer-executable instructions; and
one or more processors for executing said computer-executable instructions, comprising:
receiving a new account registration request from a user, said registration request comprising user provided registration information associated with the user;
extracting features of the user provided registration information; and
examining said features to determine whether said request is for a legitimate or abusive purpose, said examination comprises comparing said features against labeled information associated with an existing account, said labeled information corresponding to a multi-dimensional feature vector associated with raw data collected from the existing account,
when said features are determined to correspond to an abusive purpose, deny said account registration request, and
when said features are determined to correspond to a legitimate purpose, grant said account registration request.
17. The system of claim 16 , wherein said raw data comprises user activity data associated with said existing account, said user activity data being extracted from said existing account.
18. The system of claim 17 , wherein said multi-dimensional feature vector is based on an identified pattern of activity derived from said user activity data, said pattern providing an indication as to whether said existing account is legitimate or abusive, said labeled information comprising said indication.
19. The system of claim 16 , further comprising:
analyzing said new account registration request based on said examination, said analysis comprises training a classifier with said determination of the purpose of the request, wherein the classifier implements machine learning techniques in accordance with the multi-dimensional feature vector;
updating the multi-dimensional feature vector based on said analysis of said new account registration, wherein said updating occurs continuously upon determinations of new account requests; and
applying said updated multi-dimensional feature vector via the classifier to a subsequent account registration request.
20. The system of claim 16 , further comprising:
labelling said new account registration request based on said examination; and
updating an account database based on said labelling, said account database comprising user account information for user accounts on the network.