Smart retail analytics and commercial messaging

Abstract

A real-time fraud prevention system enables merchants and commercial organizations on-line to assess and protect themselves from high-risk users. A centralized database is configured to build and store dossiers of user devices and behaviors collected from subscriber websites in real-time. Real, low-risk users have webpage click navigation behaviors that are assumed to be very different than those of fraudsters. Individual user devices are distinguished from others by hundreds of points of user-device configuration data each independently maintains. A client agent provokes user devices to volunteer configuration data when a user visits respective webpages at independent websites. A collection of comprehensive dossiers of user devices is organized by their identifying information, and used calculating a fraud score in real-time. Each corresponding website is thereby assisted in deciding whether to allow a proposed transaction to be concluded with the particular user and their device.

1 . A computer network server for fraud detection for remote transactions, the server comprising:
 one or more processors;   non-transitory computer-readable storage media having computer-executable instructions stored thereon, wherein when executed by the one or more processors the computer-readable instructions cause the one or more processors to—
 receive user device data generated by a user device accessing one or more webpages of a merchant website; 
 match the user device data to a user device identity of a plurality of user device identities stored in a database, the user device identity including a plurality of attribute datapoints; 
 compare the user device data against the user device identity to generate a fraud score for the user device; and 
 transmit the fraud score to a merchant server corresponding to the merchant website. 
   
     
     
         2 . The computer network server of  claim 1 , wherein the computer-readable instructions, when executed by the one or more processors, further cause the one or more processors to decline a financial transaction requested by the user device on the merchant website based on the fraud score. 
     
     
         3 . The computer network server of  claim 1 , wherein each of the plurality of user device identities includes a corresponding plurality of attribute datapoints and at least one of the plurality of attribute datapoints comprises a smart agent profile comprising a representation of normal historical data for the corresponding attribute datapoint for the user device. 
     
     
         4 . The computer network server of  claim 3 , wherein each of the plurality of user device identities includes a classification model constructed according to one or more of: data mining logic, a neural network, case-based-reasoning, clustering, fuzzy logic, a genetic algorithm, a decision tree, and business rules. 
     
     
         5 . The computer network server of  claim 1 , wherein the user device data comprises identifying characteristics of the user device and real-time clickstream behavioral data for the user device on the merchant website. 
     
     
         6 . The computer network server of  claim 1 , wherein the user device data is received from the merchant website and the computer-readable instructions, when executed by the one or more processors the computer-readable instructions, further cause the one or more processors to receive additional user device data generated by a plurality of additional user devices accessing a plurality of additional merchant websites, the user device data and the additional user device data being collected and transmitted via endpoint clients respectively installed on the user device and each of the plurality of additional user devices. 
     
     
         7 . The computer network server of  claim 1 , wherein the comparison and the fraud score indicate the possibility of one or both of: (i) abnormal behavior of the user device, and (ii) a likelihood that the user device is inauthentic. 
     
     
         8 . Non-transitory computer-readable storage media having computer-executable instructions for fraud detection for remote transactions, wherein when executed by at least one processor the computer-readable instructions cause the at least one processor to:
 receive user device data generated by a user device accessing one or more webpages of a merchant website;   match the user device data to a user device identity of a plurality of user device identities stored in a database, the user device identity including a plurality of attribute datapoints;   compare the user device data against the user device identity to generate a fraud score for the user device; and   transmit the fraud score to a merchant server corresponding to the merchant website.   
     
     
         9 . The computer-readable storage media of  claim 8 , wherein, when executed by the one or more processors, the computer-readable instructions further cause the one or more processors to decline a financial transaction requested by the user device on the merchant website based on the fraud score. 
     
     
         10 . The computer-readable storage media of  claim 8 , wherein each of the plurality of user device identities includes a corresponding plurality of attribute datapoints and at least one of the plurality of attribute datapoints comprises a smart agent profile comprising a representation of normal historical data for the corresponding attribute datapoint for the user device. 
     
     
         11 . The computer-readable storage media of  claim 10 , wherein each of the plurality of user device identities includes a classification model constructed according to one or more of: data mining logic, a neural network, case-based-reasoning, clustering, fuzzy logic, a genetic algorithm, a decision tree, and business rules. 
     
     
         12 . The computer-readable storage media of  claim 8 , wherein the user device data comprises identifying characteristics of the user device and real-time clickstream behavioral data for the user device on the merchant website. 
     
     
         13 . The computer-readable storage media of  claim 8 , wherein the user device data is received from the merchant website and, when executed by the one or more processors, the computer-readable instructions further cause the one or more processors to receive additional user device data generated by a plurality of additional user devices accessing a plurality of additional merchant websites, the user device data and the additional user device data being collected and transmitted via endpoint clients respectively installed on the user device and each of the plurality of additional user devices. 
     
     
         14 . The computer-readable storage media of  claim 8 , wherein the comparison and the fraud score indicate the possibility of one or both of: (i) abnormal behavior of the user device, and (ii) a likelihood that the user device is inauthentic. 
     
     
         15 . A computer-implemented method for fraud detection for remote transactions comprising, via one or more transceivers and/or processors:
 receiving user device data generated by a user device accessing one or more webpages of a merchant website;   matching the user device data to a user device identity of a plurality of user device identities stored in a database, the user device identity including a plurality of attribute datapoints;   comparing the user device data against the user device identity to generate a fraud score for the user device; and   transmitting the fraud score to a merchant server corresponding to the merchant website.   
     
     
         16 . The computer-implemented method of  claim 15 , further comprising, via the one or more transceivers and/or processors, declining a financial transaction requested by the user device on the merchant website based on the fraud score. 
     
     
         17 . The computer-implemented method of  claim 15 , wherein each of the plurality of user device identities includes a corresponding plurality of attribute datapoints and at least one of the plurality of attribute datapoints comprises a smart agent profile comprising a representation of normal historical data for the corresponding attribute datapoint for the user device. 
     
     
         18 . The computer-implemented method of  claim 17 , wherein each of the plurality of user device identities includes a classification model constructed according to one or more of: data mining logic, a neural network, case-based-reasoning, clustering, fuzzy logic, a genetic algorithm, a decision tree, and business rules. 
     
     
         19 . The computer-implemented method of  claim 15 , wherein the user device data comprises identifying characteristics of the user device and real-time clickstream behavioral data for the user device on the merchant website. 
     
     
         20 . The computer-implemented method of  claim 15 , wherein the comparison and the fraud score indicate the possibility of one or both of: (i) abnormal behavior of the user device, and (ii) a likelihood that the user device is inauthentic.