Systems and methods for classifying accounts based on shared attributes with known fraudulent accounts

Patent metadata

Field	Value
Publication number	US-2022084037-A1
Application number	US-202117533054-A
Country	US
Kind code	A1
Filing date	Nov 22, 2021
Priority date	Aug 27, 2018
Publication date	Mar 17, 2022
Grant date	—

Abstract

Methods and systems are presented for classifying a particular user account as a fraudulent user account by analyzing links between the user account and two or more known fraudulent user accounts collectively. Attributes of the particular user account are compared against attributes of a plurality of known fraudulent accounts to determine that the particular user account has shared attributes with a first known fraudulent account and a second known fraudulent account. The shared attributes with the first known fraudulent account and the second known fraudulent account are analyzed collectively to determine a risk level for the particular user account. The risk level may indicate a likelihood that the particular user account corresponds to a fraudulent account.

First claim

1 . (canceled)

2 . A system, comprising:
a processor; and a non-transitory computer-readable storage medium having stored thereon instructions that are executable to cause the system to perform operations comprising:
identifying, from a plurality of electronic accounts corresponding to an electronic transaction service provider, first and second accounts classified as having a first specific account classification of a plurality of account classifications, wherein each of the plurality of electronic accounts is usable with a plurality of computer devices of the electronic transaction service provider, each of the plurality of computer devices having a processor and a memory, to perform electronic transactions with others of the plurality of electronic accounts, and wherein performing an electronic transaction between two of the plurality of electronic accounts requires an authentication step for at least one of the two of the plurality of electronic accounts;
determining that a third account corresponding to the electronic transaction service provider is linked to the first and second accounts classified as having the specific account classification, based on determining that a first set of attributes corresponding to a first set of attribute types of the third account is shared with the first account, and determining that the third account is linked to the second account based on determining that a second set of attributes corresponding to a second set of attribute types of the third account is shared with the second account;
identifying one or more common attribute types that are included in both the first set of attribute types and the second set of attribute types;
determining respective loss values corresponding to each of the one or more common attribute types; and
determining a risk level associated with the third account using a machine learning model configured to output the risk level associated with the third account using the respective loss values corresponding to the one or more common attribute types as input values, wherein the machine learning model is trained using historic data associated with accounts of the electronic transaction service provider that were previously created and that have been classified as either the first specific account classification of the plurality of account classifications or a second specific account classification of the plurality of account classifications, and wherein the risk level indicates a likelihood that the account corresponds to the first specific account classification.

3 . The system of claim 2 , wherein the first set of attribute types comprise at least one of a user device identifier, a browser type, an Internet Protocol address, a physical address, a phone number, an e-mail address, or a sold item description.

4 . The system of claim 2 , wherein the respective loss values are determined based on a first loss amount associated with the first account and a second loss amount associated with the second account.

5 . The system of claim 2 , wherein the operations further comprise:
determining the first account and the second account are linked based on a shared attribute between the first account and the second account.

6 . The system of claim 2 , wherein determining the respective loss values comprises determining a first loss value corresponding to a first attribute type of the first set of attribute types.

7 . The system of claim 2 , wherein the operations further comprise:
based on the determined risk level associated with the third account, performing a remedial action against the third account.

8 . The system of claim 7 , wherein the remedial action includes restricting access to one or more services provided via the electronic transaction service provider.

9 . A method, comprising:
accessing, by a computer system, account information for first and second accounts of a plurality of electronic accounts corresponding to an electronic transaction service provider, wherein the first and second accounts are classified as having a first specific account classification of a plurality of account classifications, wherein each of the plurality of electronic accounts is usable with a plurality of computer devices of the electronic transaction service provider, each of the plurality of computer devices having a processor and a memory, to perform electronic transactions with others of the plurality of electronic accounts, and wherein performing an electronic transaction between two of the plurality of electronic accounts requires an authentication step for at least one of the two of the plurality of electronic accounts; determining, by the computer system based on the account information, that a third account corresponding to the electronic transaction service provider is linked to the first and second accounts classified as having the specific account classification, based on determining that a first set of attributes corresponding to a first set of attribute types of the third account is shared with the first account, and determining that the third account is linked to the second account based on determining that a second set of attributes corresponding to a second set of attribute types of the third account is shared with the second account; identifying one or more common attribute types that are included in both the first set of attribute types and the second set of attribute types; determining respective loss values corresponding to each of the one or more common attribute types; and determining, by the computer system, a risk level associated with the third account using a machine learning model configured to output the risk level associated with the third account using the respective loss values corresponding to the one or more common attribute types as input values, wherein the machine learning model is trained using historic data associated with accounts of the electronic transaction service provider that were previously created and that have been classified as either the first specific account classification of the plurality of account classifications or a second specific account classification of the plurality of account classifications, and wherein the risk level indicates a likelihood that the account corresponds to the first specific account classification.

10 . The method of claim 9 , wherein determining that the third account corresponding to the electronic transaction service provider is linked to the first and second accounts comprises using attribute threshold values based on empirical data including historical account data associated with (i) accounts classified in the specific classification of the plurality of account classifications and (ii) accounts having a different classification of the plurality of account classifications.

11 . The method of claim 9 , wherein the using the attribute threshold values comprises comparing a first attribute value for the third account to first attribute values for the first and second accounts, and comprises comparing a second attribute value for the third account to second attribute values for the first and second accounts.

12 . The method of claim 9 , wherein the first set of attribute types comprise at least one of a user device identifier, a browser type, an Internet Protocol address, a physical address, a phone number, an e-mail address, or a sold item description.

13 . The method of claim 9 , wherein the respective loss values are determined based on a first loss amount associated with the first account and a second loss amount associated with the second account.

14 . The method of claim 9 , wherein determining

Assignees

• Paypal Inc

Inventors

• Fang Chuanyun
• Ran Chunmao
• Levi Itzik
• Fu Kun
• Cohen Adam
• Meron Avishay
• Hai-Reuven Doron
• Jislin Amnon

Classifications

• G06Q20/4016 Primary

  involving fraud or risk level assessment in transaction processing · CPC title

• G06F18/24143

  Distances to neighbourhood prototypes, e.g. restricted Coulomb energy networks [RCEN] · CPC title

• G06Q20/4014

  Identity check for transactions · CPC title

• H04L67/306

  User profiles · CPC title