| CPC H04L 63/0876 (2013.01) [H04L 41/16 (2013.01); H04L 63/105 (2013.01)] | 18 Claims |
|
1. A system comprising:
one or more processors; and
a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to:
receive data corresponding to a plurality of users;
receive, via a plurality of user devices associated with the plurality of users, a respective request to conduct a plurality of transactions;
determine whether the respective request satisfies one or more static rules;
responsive to determining the respective request does not satisfy the one or more static rules, determine whether a machine learning model (MLM) should be utilized to conduct a customized authentication process for the respective request;
responsive to determining the MLM should be utilized:
generate, via the MLM and based on the data, trust scores associated with the plurality of users and the plurality of user devices, wherein each trust score indicates a probability that a user device, of the plurality of user devices, is associated with a user of the plurality of users;
determine an overall fraud tolerance associated with the plurality of transactions, the overall fraud tolerance comprising a percentage;
determine a predetermined threshold based on the overall fraud tolerance;
determine whether each trust score of a plurality of trust scores exceeds the predetermined threshold thereby causing the overall fraud tolerance to exceed the percentage; and
responsive to determining a trust score of the plurality of trust scores exceeds the predetermined threshold, conduct one or more customized fraud prevention actions with respect to a corresponding user device and user,
wherein a rate of conducting the one or more customized fraud prevention actions for the plurality of users is 30 percent or less.
|