| 主权项 |
1. A method of operating an authentication gateway computer server comprising:
performing by a processor of the authentication gateway computer server: receiving, through a network interface of the authentication gateway computer server, a plurality of first eCommerce authentication requests from a plurality of first merchant nodes separate from the authentication gateway computer server, wherein respective ones of the plurality of first eCommerce authentication requests comprise first cardholder information; receiving, through the network interface of the authentication gateway computer server, feedback information corresponding to at least one of the plurality of first eCommerce authentication requests; training, using training circuitry of the authentication gateway computer server, a non-linear neural network model based on a comparison of the first cardholder information provided by the plurality of first eCommerce authentication requests and the feedback information corresponding to the at least one of the plurality of first eCommerce authentication requests to create a customized non-linear neural network model customized to the plurality of first eCommerce authentication requests received by the authentication gateway computer server,
wherein the customized non-linear neural network model comprises an input layer comprising input nodes, a sequence of neural network layers each comprising a plurality of weight nodes, and an output layer comprising an output node; receiving, through the network interface of the authentication gateway computer server, a second eCommerce authentication request from a second merchant node, the second eCommerce authentication request having content comprising second cardholder information; generating a risk score for the second eCommerce authentication request based on comparison of the second cardholder information of the second eCommerce authentication request to first cardholder information of the first eCommerce authentication requests of the plurality of first merchant nodes by processing a plurality of items of the content of the second eCommerce authentication request through different inputs of the customized non-linear neural network model to generate the risk score for the second eCommerce authentication request,
wherein processing the plurality of items of the content of the second eCommerce authentication request through different inputs of the customized non-linear neural network model comprises:operating the input nodes of the input layer to each receive a different one of items of the content of the second eCommerce authentication request and output a value;operating the weight nodes of a first one of the sequence of neural network layers using weight values to mathematically combine values that are output by the input nodes to generate combined values;operating the weight nodes of a last one of the sequence of neural network layers using weight values to mathematically combine the combined values from a plurality of weight nodes of a previous one of the sequence of neural network layers to generate combined values; andoperating the output node of the output layer to combine the combined values from the weight nodes of the last one of the sequence of neural network layers to generate the risk score; and selectively routing the second eCommerce authentication request through the network interface of the authentication gateway computer server to an authentication computer server, separate from the authentication gateway computer server, for additional authentication based on the risk score. |
