Machine learning and validation of account names, addresses, and/or identifiers
Systems and methods are disclosed for determining if an account identifier is computer-generated. One method includes receiving the account identifier, dividing the account identifier into a plurality of fragments, and determining one or more features of at least one of the fragments. The method further includes determining the commonness of at least one of the fragments, and determining if the account identifier is computer-generated based on the features of at least one of the fragments, and the commonness of at least one of the fragments.
1. A computer-implemented method for determining if an electronic account identifier is computer-generated, comprising:
receiving the electronic account identifier;
determining, based on the electronic account identifier, a plurality of fragments, the plurality of fragments comprising all possible identifier fragments of a predetermined character length;
determining one or more features of at least one of the fragments, the one or more features of the at least one of the fragments comprising an alphanumeric character type;
determining a percentile of commonness of at least one of the fragments by comparing the at least one of the fragments with a second plurality of fragments associated with a plurality of electronic account identifiers;
determining, by a computer, if the electronic account identifier is computer-generated beyond a predetermined confidence threshold based on the features of at least one of the fragments, and the percentile of commonness of at least one of the fragments; and
said computer determining if the electronic account identifier is computer-generated with a probabilistic classifier model trained with a training set of a plurality of electronic account identifiers, wherein each of the plurality of electronic account identifiers is determined to be either a genuine human-generated identifier or a computer-generated identifier.
2. The method of claim 1 , wherein determining if the electronic account identifier is computer-generated comprises providing the features of at least one of the fragments, and the percentile of commonness of at least one of the fragments, to the probabilistic classifier model.
3. The method of claim 1 , further comprising:
determining one or more features of the electronic account identifier by counting characters by character type.
4. The method of claim 1 , wherein determining the percentile of commonness of at least one of the fragments comprises determining the frequency of occurrence of the at least one of the fragments relative to a plurality of fragments in a data store.
5. The method of claim 1 , wherein at least one of the fragments is truncated to contain only consonants.
6. The method of claim 1 , wherein each character of at least one of the fragments is hashed according to character type.
7. The method of claim 6 , wherein each character type is selected from a group including consonant, vowel, number, and punctuation mark.
8. A system for determining if an electronic account identifier is computer-generated, the system including:
at least one data storage device storing instructions determining if an electronic account identifier is computer-generated; and
at least one computer processor configured to execute the instructions to perform operations including:
receiving the electronic account identifier;
determining, based on the electronic account identifier, a plurality of fragments, the plurality of fragments comprising all possible identifier fragments of a predetermined character length;
determining one or more features of at least one of the fragments, the one or more features of the at least one of the fragments comprising an alphanumeric character type;
determining a percentile of commonness of at least one of the fragments by comparing the at least one of the fragments with a second plurality of fragments associated with a plurality of electronic account identifiers;
determining, by the computer processor, if the electronic account identifier is computer-generated beyond a predetermined confidence threshold based on the features of at least one of the fragments, and the percentile of commonness of at least one of the fragments; and
said computer processor determining if the electronic account identifier is computer-generated with a probabilistic classifier model trained with a training set of a plurality of electronic account identifiers, wherein each of the plurality of electronic account identifiers is determined to be either a genuine human-generated identifier or a computer-generated identifier.
9. The system of claim 8 , wherein determining if the electronic account identifier is computer-generated comprises providing the features of at least one of the fragments, and the percentile of commonness of at least one of the fragments, to the probabilistic classifier model.
10. The system of claim 8 , wherein the operations further comprise:
determining one or more features of the electronic account identifier by counting characters by character type.
11. The system of claim 8 , wherein determining the percentile of commonness of at least one of the fragments comprises determining the frequency of occurrence of the at least one of the fragments relative to a plurality of fragments in a data store.
12. The system of claim 8 , wherein at least one of the fragments is truncated to contain only consonants.
13. The system of claim 8 , wherein each character of at least one of the fragments is hashed according to character type.
14. A non-transitory computer-readable medium storing instructions that, when executed by a computer processor, cause the computer processor to perform operations for determining whether an electronic account identifier is computer-generated, the operations including:
receiving the electronic account identifier;
determining, based on the electronic account identifier, a plurality of fragments, the plurality of fragments comprising all possible identifier fragments of a predetermined character length;
determining one or more features of at least one of the fragments, the one or more features of the at least one of the fragments comprising an alphanumeric character type;
determining a percentile of commonness of at least one of the fragments by comparing the at least one of the fragments with a second plurality of fragments associated with a plurality of electronic account identifiers;
determining, by the computer processor, if the electronic account identifier is computer-generated beyond a predetermined confidence threshold based on the features of at least one of the fragments, and the percentile of commonness of at least one of the fragments; and
said computer processor determining if the electronic account identifier is computer-generated with a probabilistic classifier model trained with a training set of a plurality of electronic account identifiers, wherein each of the plurality of electronic account identifiers is determined to be either a genuine human-generated identifier or a computer-generated identifier.
15. The non-transitory computer-readable medium of claim 14 , wherein determining if the electronic account identifier is computer-generated comprises providing the features of at least one of the fragments, and the percentile of commonness of at least one of the fragments, to the probabilistic classifier model.
16. The non-transitory computer-readable medium of claim 14 , wherein determining the percentile of commonness of at least one of the fragments comprises determining the frequency of occurrence of the at least one of the fragments relative to a plurality of fragments in a data store.
17. The non-transitory computer-readable medium of claim 14 , wherein each character of at least one of the fragments is hashed according to character type.