Machine learning engine for fraud detection during cross-location online transaction processing

Abstract

A machine learning engine for fraud detection related to cross-location online transaction processing may be trained using artificial intelligence techniques and used according to techniques discussed herein. An account may be used to electronically process a transaction for an item in a foreign location, such as a new city or country. The transaction may be identified as potentially fraudulent based on the item and/or location of purchase. A service provider may identify a vertical, such as an item type, for the transaction, and may determine the account's propensity to purchase within that vertical in the new location and the merchant's propensity to sell within that vertical to the account's location or shipping address. Based on the propensities, the service provider may utilize one or more risk rules with a risk assessment engine to determine transaction processing risk and whether to proceed with transaction processing.

1 . (canceled) 
     
     
         2 . A system, comprising:
 a processor; and   a non-transitory computer-readable medium having stored thereon instructions that are executable to cause the system to perform operations comprising:   based on a processing request for a transaction for an entity located at a first location, determining a first vertical categorization for the transaction;   determining a second location associated with an online account corresponding to the transaction;   identifying a vertical cluster associated with the online account based on the first location and the second location, wherein the vertical cluster includes a second vertical categorization corresponding to a previous transaction conducted by the online account;   determining a probability, using a machine learning engine, of a user of the online account to participate in the transaction within the first vertical categorization based on the second vertical categorization;   using one or more transaction risk assessment rules and the probability of the user to participate in the transaction, assigning a risk score to the transaction; and   reporting the assigned risk score.   
     
     
         3 . The system of  claim 2 , wherein the machine learning engine has been trained using cross-location online data comprising a plurality of transactions from a plurality of user accounts having a corresponding respective plurality of locations. 
     
     
         4 . The system of  claim 2 , wherein the probability comprises a probability associated with purchase transactions by the online account and a plurality of other accounts associated with the second location for purchase of items within the first vertical categorization from entities at the first location. 
     
     
         5 . The system of  claim 4 , wherein prior to identifying the vertical cluster, the operations further comprise:
 identifying one or more shared verticals for the online account and the plurality of other accounts using at least the second vertical categorization; and   determining the vertical cluster comprising the online account and the plurality of other accounts based on identifying the one or more shared verticals.   
     
     
         6 . The system of  claim 5 , wherein the vertical cluster is determined based on clustering account transaction data for the online account and the plurality of other accounts using k-means clustering. 
     
     
         7 . The system of  claim 2 , wherein the operations further comprise:
 reporting the assigned risk score to an entity assessing an overall transaction risk for the transaction.   
     
     
         8 . The system of  claim 2 , wherein the operations further comprise:
 making a determination that the transaction should require additional authentication to process the transaction with the account based on the risk score; and   providing the determination that the transaction should require the additional authentication.   
     
     
         9 . The system of  claim 2 , wherein the first location comprises a first country where the entity sells items within the first vertical categorization, wherein the second location comprises a second country of use of the online account, and wherein the transaction comprises a cross-border transaction with the entity using the online account. 
     
     
         10 . The system of  claim 2 , wherein the operations further comprise: determining an account value level for the online account, wherein the risk score is further based on the account value level. 
     
     
         11 . The system of  claim 1 , wherein the operations further comprise:
 based on the assigned risk score, facilitating processing of the transaction; and   outputting a transaction processing result to a device associated with the processing request.   
     
     
         12 . A method, comprising:
 receiving an indication, at a computer system, that a first user device has made a processing request for a transaction for an entity located at a first location;   determining, by the computer system, a first vertical categorization for the transaction;   determining, by the computer system, a second location associated with an online account corresponding to the transaction;   identifying, by the computer system, a vertical cluster associated with the online account based on the first location and the second location, wherein the vertical cluster includes a second vertical categorization corresponding to a previous transaction conducted by the online account;   determining a probability, using a machine learning engine, of a user of the online account to participate in the transaction within the first vertical categorization based on the second vertical categorization; and   the computer system using one or more transaction risk assessment rules and the probability of the user to participate in the transaction, assigning a risk score to the transaction.   
     
     
         13 . The method of  claim 12 , further comprising assigning a risk score to the transaction based on device information corresponding to the first user device. 
     
     
         14 . The method of  claim 13 , wherein the device information comprises an IP address for the first user device. 
     
     
         15 . The method of  claim 12 , further comprising transmitting the assigned risk score to a transaction service provider computing device. 
     
     
         16 . The method of  claim 15 , wherein the transaction service provider computing device is located on a different communications network than the computer system. 
     
     
         17 . A non-transitory computer-readable medium having stored thereon instructions executable by a computer system to cause the computer system to perform operations comprising:
 based on a processing request for a transaction for an entity located at a first location, determining a first vertical categorization for the transaction;   determining a second location associated with an online account corresponding to the transaction;   identifying a vertical cluster associated with the online account based on the first location and the second location, wherein the vertical cluster includes a second vertical categorization corresponding to a previous transaction conducted by the online account;   determining a probability, using a machine learning engine, of a user of the online account to participate in the transaction within the first vertical categorization based on the second vertical categorization;   using one or more transaction risk assessment rules and the probability of the user to participate in the transaction, assigning a risk score to the transaction; and   reporting the assigned risk score.   
     
     
         18 . The non-transitory computer-readable medium of  claim 17 , wherein the machine learning engine has been trained using cross-location online data comprising a plurality of transactions from a plurality of user accounts having a corresponding respective plurality of locations. 
     
     
         19 . The non-transitory computer-readable medium of  claim 17 , wherein the probability comprises a probability associated with purchase transactions by the online account and a plurality of other accounts associated with the second location for purchase of items within the first vertical categorization from entities at the first location. 
     
     
         20 . The non-transitory computer-readable medium of  claim 17 , wherein the operations further comprise:
 reporting the assigned risk score to an entity assessing an overall transaction risk for the transaction.   
     
     
         21 . The non-transitory computer-readable medium of  claim 17 , wherein the operations further comprise determining the risk score based on an amount of the transaction and a type of good or service in the transaction.